The locations of pigs in the group housing enable activity monitoring and improve animal welfare. Vision-based methods for tracking individual pigs are noninvasive but have low tracking accuracy owing to long-term pig occlusion. In this study, we developed a vision-based method that accurately tracked individual pigs in group housing. We prepared and labeled datasets taken from an actual pig farm, trained a faster region-based convolutional neural network to recognize pigs’ bodies and heads, and tracked individual pigs across video frames. To quantify the tracking performance, we compared the proposed method with the global optimization (GO) method with the cost function and the simple online and real-time tracking (SORT) method on four additional test datasets that we prepared, labeled, and made publicly available. The predictive model detects pigs’ bodies accurately, with F1-scores of 0.75 to 1.00, on the four test datasets. The proposed method achieves the largest multi-object tracking accuracy (MOTA) values at 0.75, 0.98, and 1.00 for three test datasets. In the remaining dataset, the proposed method has the second-highest MOTA of 0.73. The proposed tracking method is robust to long-term occlusion, outperforms the competitive baselines in most datasets, and has practical utility in helping to track individual pigs accurately.
A BRIEF OVERVIEW ON DIFFERENT ANIMAL DETECTION METHODSsipij
Researches based on animal detection plays a very vital role in many real life applications. Applications
which are very important are preventing animal vehicle collision on roads, preventing dangerous animal
intrusion in residential area, knowing locomotive behavioural of targeted animal and many more. There
are limited areas of research related to animal detection. In this paper we will discuss some of these areas
for detection of animals.
This document discusses using machine learning to help conserve endangered species. It begins by outlining the threats facing endangered species from climate change, habitat loss, and human activity. Machine learning can help overcome challenges to monitoring endangered species by analyzing large datasets from camera traps, satellite imagery, and acoustic recordings to identify and track species. Temperature change also significantly impacts animal populations, so the proposed system will compile temperature and species count data to predict how populations may change in future years. The document reviews several papers applying techniques like CNNs, YOLO, SSD to identify species in camera trap images with high accuracy to help conservation efforts.
A Survey on Various Animal Health Monitoring and Tracking TechniquesIRJET Journal
This document summarizes several existing techniques for animal health monitoring and tracking. It discusses sensors used to monitor temperature, heart rate, pulse rate, and respiration in animals. ZigBee modules are used to transmit sensor data to a GUI. The document then reviews several past studies on monitoring animal feeding behaviors, vital signs, localization using RFID, implantable biosensors, and movement tracking using GPS collars. It concludes that an integrated system for both health monitoring and movement tracking is needed. Future work aims to develop a wearable device incorporating sensors and wireless charging to monitor animals unobtrusively.
AN APPROACH TO DESIGN A RECTANGULAR MICROSTRIP PATCH ANTENNA IN S BAND BY TLM...prj_publication
In this paper we have designed a rectangular microstrip antenna in ‘S’ band
transmission line model. The S band frequency ranges from 2 GHz to 4GHz for wireless
application. The desired frequency is chosen to be 2.4 GHz at which the patch antenna is
designed to improve the bandwidth. After calculating the various parameters such as width,
effective dielectric constant, effective length and actual length. The antenna impedance is
matched to 50 ohm using inset feed. The results are obtained (Input Impedance, reflection
coefficient, SWR and bandwidth) by using MATLAB software.
Pattern recognition using video surveillance for wildlife applicationsprjpublications
This document summarizes a research paper that proposes a wildlife monitoring system using video surveillance and pattern recognition. The system uses motion detection to capture images when movement is detected. A pattern recognition module then analyzes the images using Histogram of Oriented Gradients (HOG) to distinguish between harmful and harmless animals. If a harmful animal is identified, the system notifies authorities of the animal type and location using GSM and GPS modules. The researchers tested the system using a database of animal images and found that HOG provided accurate classification of tigers and other animals.
This document summarizes a seminar topic on animal monitoring using the Internet of Things. It discusses using sensors on animal collars to monitor body temperature, rumination, heart rate, and location. The hardware architecture uses collars on animals to collect sensor data and beacons to track location. A cloud platform analyzes the collected data to provide information to farmers on animal behavior and health. Potential applications include early detection of health issues in animals and understanding animal movement patterns. Future areas of research may involve using satellite tracking and camera traps to monitor wild animals. The conclusion evaluates machine learning algorithms for categorizing animal posture data collected from sensor collars.
Mobile sensing in Aedes aegypti larva detection with biological feature extra...journalBEEI
According to WHO, Dengue fever is the most critical and most rapidly mosquito-borne disease in the world over 50 years. Currently, the presence and detection of Aedes aegypti larvae (dengue-mosquitoes vector’s) are only quantified by human perception. In large-scale data, we need to automate the process of larvae detection and classification as much as possible. This paper introduces the new method to automate Aedes larvae. We use Culex larva for comparison. This method consists of data acquisition of recorded motion video, spatial movement patterns, and image statistical classification. The results show a significant difference between the biological movements of Aedes aegypti and Culex under the same environmental conditions. In 50 videos consisting of 25 Aedes larvae videos and 25 Culex larvae videos, the accuracy was 84%.
Animal Breed Classification And Prediction Using Convolutional Neural Network...Allison Thompson
This document describes a study that uses a convolutional neural network (CNN) to classify and predict breeds of primates using a dataset of 10 monkey species images. The CNN model was trained on the image dataset and achieved 80.5% accuracy on the training set and 73.53% accuracy on the validation set after 20 epochs of training. The trained model was able to accurately predict the primate breeds in the dataset. The researchers aim to use this type of automated primate breed identification to help conservation efforts and protect endangered species from extinction.
A BRIEF OVERVIEW ON DIFFERENT ANIMAL DETECTION METHODSsipij
Researches based on animal detection plays a very vital role in many real life applications. Applications
which are very important are preventing animal vehicle collision on roads, preventing dangerous animal
intrusion in residential area, knowing locomotive behavioural of targeted animal and many more. There
are limited areas of research related to animal detection. In this paper we will discuss some of these areas
for detection of animals.
This document discusses using machine learning to help conserve endangered species. It begins by outlining the threats facing endangered species from climate change, habitat loss, and human activity. Machine learning can help overcome challenges to monitoring endangered species by analyzing large datasets from camera traps, satellite imagery, and acoustic recordings to identify and track species. Temperature change also significantly impacts animal populations, so the proposed system will compile temperature and species count data to predict how populations may change in future years. The document reviews several papers applying techniques like CNNs, YOLO, SSD to identify species in camera trap images with high accuracy to help conservation efforts.
A Survey on Various Animal Health Monitoring and Tracking TechniquesIRJET Journal
This document summarizes several existing techniques for animal health monitoring and tracking. It discusses sensors used to monitor temperature, heart rate, pulse rate, and respiration in animals. ZigBee modules are used to transmit sensor data to a GUI. The document then reviews several past studies on monitoring animal feeding behaviors, vital signs, localization using RFID, implantable biosensors, and movement tracking using GPS collars. It concludes that an integrated system for both health monitoring and movement tracking is needed. Future work aims to develop a wearable device incorporating sensors and wireless charging to monitor animals unobtrusively.
AN APPROACH TO DESIGN A RECTANGULAR MICROSTRIP PATCH ANTENNA IN S BAND BY TLM...prj_publication
In this paper we have designed a rectangular microstrip antenna in ‘S’ band
transmission line model. The S band frequency ranges from 2 GHz to 4GHz for wireless
application. The desired frequency is chosen to be 2.4 GHz at which the patch antenna is
designed to improve the bandwidth. After calculating the various parameters such as width,
effective dielectric constant, effective length and actual length. The antenna impedance is
matched to 50 ohm using inset feed. The results are obtained (Input Impedance, reflection
coefficient, SWR and bandwidth) by using MATLAB software.
Pattern recognition using video surveillance for wildlife applicationsprjpublications
This document summarizes a research paper that proposes a wildlife monitoring system using video surveillance and pattern recognition. The system uses motion detection to capture images when movement is detected. A pattern recognition module then analyzes the images using Histogram of Oriented Gradients (HOG) to distinguish between harmful and harmless animals. If a harmful animal is identified, the system notifies authorities of the animal type and location using GSM and GPS modules. The researchers tested the system using a database of animal images and found that HOG provided accurate classification of tigers and other animals.
This document summarizes a seminar topic on animal monitoring using the Internet of Things. It discusses using sensors on animal collars to monitor body temperature, rumination, heart rate, and location. The hardware architecture uses collars on animals to collect sensor data and beacons to track location. A cloud platform analyzes the collected data to provide information to farmers on animal behavior and health. Potential applications include early detection of health issues in animals and understanding animal movement patterns. Future areas of research may involve using satellite tracking and camera traps to monitor wild animals. The conclusion evaluates machine learning algorithms for categorizing animal posture data collected from sensor collars.
Mobile sensing in Aedes aegypti larva detection with biological feature extra...journalBEEI
According to WHO, Dengue fever is the most critical and most rapidly mosquito-borne disease in the world over 50 years. Currently, the presence and detection of Aedes aegypti larvae (dengue-mosquitoes vector’s) are only quantified by human perception. In large-scale data, we need to automate the process of larvae detection and classification as much as possible. This paper introduces the new method to automate Aedes larvae. We use Culex larva for comparison. This method consists of data acquisition of recorded motion video, spatial movement patterns, and image statistical classification. The results show a significant difference between the biological movements of Aedes aegypti and Culex under the same environmental conditions. In 50 videos consisting of 25 Aedes larvae videos and 25 Culex larvae videos, the accuracy was 84%.
Animal Breed Classification And Prediction Using Convolutional Neural Network...Allison Thompson
This document describes a study that uses a convolutional neural network (CNN) to classify and predict breeds of primates using a dataset of 10 monkey species images. The CNN model was trained on the image dataset and achieved 80.5% accuracy on the training set and 73.53% accuracy on the validation set after 20 epochs of training. The trained model was able to accurately predict the primate breeds in the dataset. The researchers aim to use this type of automated primate breed identification to help conservation efforts and protect endangered species from extinction.
Detection and classification of animals using Machine Learning and Deep LearningIRJET Journal
This document presents a proposed animal detection and classification system using machine learning and deep learning techniques. The system aims to detect and identify animals from camera trap images to address the problem of human-animal conflict. It will first generate region proposals of animal objects from images and then use techniques like XGBoost, PSO and CNN to detect and classify the animals. These techniques will determine if the region proposals contain true animals or background patches and then identify the animal species. The system is intended to be used for applications like detecting animal intrusions, preventing animal-vehicle collisions, and monitoring agriculture fields. It discusses related work on existing animal detection methods and their limitations. The proposed system architecture includes modules for image collection, preprocessing, dataset creation,
A Literature Research Review On Animal Intrusion Detection And Repellent SystemsScott Bou
This document provides a literature review of research on animal intrusion detection and repellent systems. It discusses various sensor technologies, imaging methods, and machine learning algorithms that have been used to detect animal movements and identify animal species in images. These include passive infrared sensors to detect movement, cameras to capture images, convolutional neural networks to classify images, and speakers or lights to repel animals in a non-harmful way. The review covers research on using these techniques for applications like preventing human-animal conflicts in agricultural fields and monitoring wildlife.
This document discusses developing a pet care application using machine learning. It aims to use CNNs to predict dog breeds from photos and decision trees to predict diseases. Accurately identifying breeds and diseases early could help pet owners provide better care and save pet lives. The document reviews related work using deep learning for tasks like image classification. It proposes a system to first use a CNN for breed prediction from images then evaluate algorithms like decision trees for disease prediction from pet data. The goal is to integrate machine learning into veterinary healthcare to optimize treatment and enable early diagnosis.
Snake Detection in Agricultural Fields using IoTIRJET Journal
1. The document discusses a system to detect snakes in agricultural fields using IoT technology and deep learning techniques. Sensors placed around field borders can detect snake movements and capture images, which are then analyzed using convolutional neural networks to identify if the snake is venomous.
2. If a venomous snake is detected, farmers would be alerted using a buzzer to take precautions. The system aims to reduce snake bite deaths among farmers and conserve snake populations in the area.
3. The document reviews several related works involving using sensors and deep learning to detect animals harming agriculture, monitor home intrusions, and identify snake species for medical treatment.
A Survey on Smart Devices for Object and Fall DetectionIRJET Journal
This document summarizes a survey on smart devices for object and fall detection. It discusses how sensors and microcontrollers can be used to create wearable alert devices for the elderly that detect falls and send location information to concerned contacts. It also describes how ultrasonic sensors and smart glasses can detect obstacles to help blind or visually impaired people navigate safely. The document reviews several existing studies on vision-based and sensor-based fall detection systems and identifies challenges in real-world deployment, usability, and user acceptance of emerging technologies.
Endangered Bird Species Classification Using Machine Learning TechniquesIRJET Journal
This document presents research on developing a machine learning model to classify endangered bird species using images. The researchers created a dataset of over 7,000 images from 20 endangered bird species and trained convolutional neural network (CNN) models on the data. They tested various hyperparameters and techniques, such as data augmentation, to improve the model's performance. Their best model achieved a promising accuracy of 98% on the test dataset. The researchers conclude that automated bird species identification using machine learning can help conservation efforts by aiding population monitoring and tracking, which supports endangered bird preservation.
Real Time Object Detection with Audio Feedback using Yolo v3ijtsrd
In this paper, we propose a system that combines real time object detection using the YOLOv3 algorithm with audio feedback to assist visually impaired individuals in locating and identifying objects in their surroundings. The YOLOv3 algorithm is a state of the art object detection algorithm that has been used in numerous studies for various applications. Audio feedback has also been studied in previous research as a useful tool for assisting visually impaired individuals. Our proposed system builds on the effectiveness of both these technologies to provide a valuable tool for improving the independence and quality of life of visually impaired individuals. We present the architecture of our proposed system, which includes a YOLOv3 model for object detection and a text to speech engine for providing audio feedback. We also present the results of our experiments, which demonstrate the effectiveness of our system in detecting and identifying objects in real time. Our proposed system can be used in various settings, such as indoor and outdoor environments, and can assist visually impaired individuals in various activities such as the navigation and object identification. Dr. K. Nagi Reddy | K. Sreeja | M. Sreenivasulu Reddy | K. Sireesha | M. Triveni "Real Time Object Detection with Audio Feedback using Yolo_v3" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-7 | Issue-2 , April 2023, URL: https://www.ijtsrd.com.com/papers/ijtsrd55158.pdf Paper URL: https://www.ijtsrd.com.com/engineering/electronics-and-communication-engineering/55158/real-time-object-detection-with-audio-feedback-using-yolov3/dr-k-nagi-reddy
RAILWAY-ELEPHANT CONFLICT MINIMISATION USING RADIO FREQUENCY TECHNOLOGYIRJET Journal
This document discusses the development of a system to detect elephants crossing railway tracks using radio frequency technology in order to minimize conflicts between elephants and trains in India. The system uses a YOLO model to detect elephants via camera monitoring the tracks. When an elephant is detected, radio frequency modules transmit signals to alert the nearby locomotive pilot and station master. The system also sends text messages and emails to notify the station master. The goal is to reduce accidents between elephants and trains by notifying train operators in time for them to stop or slow down if an elephant is spotted on the tracks.
This document presents research on developing an automated system for fish species detection using deep learning and the MobileNetV2 architecture. The researchers assembled a large dataset of fish photos and used MobileNetV2 for image classification. MobileNetV2 is efficient and effective for this task as it balances accuracy and computational performance. Through training and evaluation, the researchers demonstrated that their method achieves accurate fish species detection and categorization while maintaining computational efficiency compared to other techniques. Their proposed application aims to streamline aquatic ecosystem monitoring and conservation efforts by providing a precise and efficient means of assessing fish populations.
IRJET- A Leading Hand for the Blind –A ReviewIRJET Journal
This document reviews various technologies and devices that have been developed to assist visually impaired individuals in navigating and performing daily tasks. It discusses how advances in technologies like RFID, GPS, voice assistance, and image processing have enabled new discoveries to help the blind. The document then reviews several existing smart stick and navigation systems that use sensors like ultrasonic, infrared, and PIR along with technologies like GPS, GSM, Bluetooth and microcontrollers to guide and provide information to visually impaired users. However, many of these systems have limitations such as only working for predefined routes, inability to determine obstacle distances, or reliance on smartphone apps which may not always provide accurate information. Overall, the document examines the history and need for aids for the blind
Wildlife Identification using Object Detection using Computer Vision and YOLOIRJET Journal
This document discusses using the YOLO (You Only Look Once) algorithm for wildlife identification and monitoring through computer vision. YOLO is a real-time object detection framework that can efficiently process video frames to identify and track wildlife in order to provide insights about population dynamics, behaviors, and potential threats to support conservation efforts. The researchers trained the YOLO model on wildlife datasets to enable accurate recognition and classification of different species from CCTV camera feeds of wildlife habitats. The real-time capabilities of YOLO allow for continuous monitoring of wildlife populations and analysis of animal behaviors.
Anti-poaching System to Detect Poachers and Conserve Forest EcosystemIRJET Journal
This document proposes an anti-poaching system that uses sensors to detect poaching activity in forests and notify authorities. The system uses a cell phone detector sensor to detect signals from cell phones between 0.8-2.5GHz and trigger an alert with the phone's location. It also uses a PIR motion sensor with a range of 7-12 meters to detect intruders, then triggers a camera to take an image and send it along with location data via GPRS to a central server for authorities to monitor. The system is designed to be low-power, ruggedized and mounted in forests to automatically detect and report poaching activities to help conservation efforts.
Automatic detection of broiler’s feeding and aggressive behavior using you on...IAESIJAI
The high market demand for broiler chickens requires that chicken farmers improve their production performance. Production cost and poultry welfare are important competitiveness aspects in the poultry industry. To optimize these aspects, chicken behavior such as feeding and aggression needs to be observed continuously. However, this is not practically done entirely by humans. Implementation of precision live stock farming with deep learning can provide continuous, real-time and automated decisions. In this study, the you only look once version 4 (YOLOv4) architecture is used to detect feeding and aggressive chicken behavior. The data used includes 1,045 feeding bounding boxes and 753 aggressive bounding boxes. The model training is performed using the k-fold cross validation method. The best mean average precision (mAP) values obtained were 99.98% for eating behavior and 99.4% for aggressive behavior.
Automatic identification of animal using visual and motion saliencyeSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
IRJET- GPS Arduino based Tracking and Alarm System for Protection of Wildlife...IRJET Journal
This document describes a GPS-based tracking and alarm system to protect wildlife animals. The key components are a GPS module to track animal locations, a temperature sensor to monitor animal health, and RFID tags to identify individual animals. The system works as follows:
1) A GPS module tracks animal locations continuously and sends the data to an IoT platform.
2) A temperature sensor monitors each animal's temperature frequently and alerts if levels change.
3) RFID tags identify individual animals, and an RFID reader sounds an alarm if an animal crosses its boundary.
4) All sensor data on location, temperature, and animal ID are continuously updated on the IoT platform for remote monitoring without direct human involvement.
Automatic motion tracking system for analysis of insect behaviorWookjin Choi
Undergraduate research.
We present a multi-object tracking system to track small insects such as ants and bees. Motion-based object tracking recognizes the movements of objects in videos using information extracted from the given video frames. We applied several computer vision techniques, such as blob detection and appearance matching, to track ants. Moreover, we discussed different object detection methodologies and investigated the various challenges of object detection, such as illumination variations and blob merge/split. The proposed system effectively tracked multiple objects in various environments.
AUTOMATIC REAL-TIME RAILWAY FISHPLATE MONITORINGSYSTEM FOR EARLY WARNING USIN...IRJET Journal
This document describes an automatic real-time railway fishplate monitoring system using IoT to detect loosened fishplates and provide early warnings. The system uses proximity sensors to detect if fishplate bolts are loosened, an Arduino microcontroller to process the sensor data, a NodeMCU with WiFi to transmit data to the cloud, a GPS module to track the exact location of faults, and a mobile app to view fault locations and warnings. The system aims to reduce railway accidents by continuously and remotely monitoring the condition of fishplates. An experiment showed the system could successfully detect loosened bolts, track locations, and display warnings on a mobile app in real-time.
IRJET- Hybrid Approach to Reduce Energy Utilization in Wireless Sensor Networ...IRJET Journal
This document discusses using bio-inspired techniques to reduce energy utilization in wireless sensor networks. It begins by introducing wireless sensor networks and describing energy consumption as a major challenge. It then discusses several bio-inspired algorithms that could be applied for routing in wireless sensor networks, including ant colony optimization, artificial bee colony optimization, genetic algorithms, and particle swarm optimization. The document reviews related work applying these algorithms to optimize various wireless sensor network performance metrics like energy efficiency. It proposes developing a new routing algorithm based on swarm intelligence techniques to improve wireless sensor network performance.
Detection of Aedes aegypti larvae using single shot multibox detector with tr...journalBEEI
The flavivirus epidemiology has reached an alarming rate which haunts the world population including Malaysia. In fact, World Health Organization has proposed and practised many methods of vector control through environmental management, chemical and biological orientations but still cannot fully overcome the problem. This paper proposed a detection of Aedes Aegypti larvae in water storage tank using Single Shot Multibox Detector with transfer learning. The objective of the study was to acquire the training and the performance metrics of the detection. The detection was done using SSD with Inception_V2 through transfer learning. The experimental results revealed that the probability detection scored more than 80% accuracies and there was no false alarm. These results demonstrate the effectiveness of the model approach.
A Survey on Person Detection for Social Distancing and Safety Violation Alert...IRJET Journal
This document discusses methods for monitoring social distancing using video surveillance and deep learning techniques. It describes how faster R-CNN, single shot detector (SSD) and YOLO v3 deep learning models can be used to detect people in video frames and calculate the distance between individuals to determine if social distancing guidelines are being followed. If distances between people are found to be unsafe, the system can send alerts or cautions. The methodology is intended to help prevent the spread of COVID-19 by monitoring adherence to social distancing and triggering warnings if safety violations are detected.
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
More Related Content
Similar to Robust individual pig tracking (Keywords: Multi-object tracking, Performance evaluation, Pig detection, Pig localization, Pig tracking)
Detection and classification of animals using Machine Learning and Deep LearningIRJET Journal
This document presents a proposed animal detection and classification system using machine learning and deep learning techniques. The system aims to detect and identify animals from camera trap images to address the problem of human-animal conflict. It will first generate region proposals of animal objects from images and then use techniques like XGBoost, PSO and CNN to detect and classify the animals. These techniques will determine if the region proposals contain true animals or background patches and then identify the animal species. The system is intended to be used for applications like detecting animal intrusions, preventing animal-vehicle collisions, and monitoring agriculture fields. It discusses related work on existing animal detection methods and their limitations. The proposed system architecture includes modules for image collection, preprocessing, dataset creation,
A Literature Research Review On Animal Intrusion Detection And Repellent SystemsScott Bou
This document provides a literature review of research on animal intrusion detection and repellent systems. It discusses various sensor technologies, imaging methods, and machine learning algorithms that have been used to detect animal movements and identify animal species in images. These include passive infrared sensors to detect movement, cameras to capture images, convolutional neural networks to classify images, and speakers or lights to repel animals in a non-harmful way. The review covers research on using these techniques for applications like preventing human-animal conflicts in agricultural fields and monitoring wildlife.
This document discusses developing a pet care application using machine learning. It aims to use CNNs to predict dog breeds from photos and decision trees to predict diseases. Accurately identifying breeds and diseases early could help pet owners provide better care and save pet lives. The document reviews related work using deep learning for tasks like image classification. It proposes a system to first use a CNN for breed prediction from images then evaluate algorithms like decision trees for disease prediction from pet data. The goal is to integrate machine learning into veterinary healthcare to optimize treatment and enable early diagnosis.
Snake Detection in Agricultural Fields using IoTIRJET Journal
1. The document discusses a system to detect snakes in agricultural fields using IoT technology and deep learning techniques. Sensors placed around field borders can detect snake movements and capture images, which are then analyzed using convolutional neural networks to identify if the snake is venomous.
2. If a venomous snake is detected, farmers would be alerted using a buzzer to take precautions. The system aims to reduce snake bite deaths among farmers and conserve snake populations in the area.
3. The document reviews several related works involving using sensors and deep learning to detect animals harming agriculture, monitor home intrusions, and identify snake species for medical treatment.
A Survey on Smart Devices for Object and Fall DetectionIRJET Journal
This document summarizes a survey on smart devices for object and fall detection. It discusses how sensors and microcontrollers can be used to create wearable alert devices for the elderly that detect falls and send location information to concerned contacts. It also describes how ultrasonic sensors and smart glasses can detect obstacles to help blind or visually impaired people navigate safely. The document reviews several existing studies on vision-based and sensor-based fall detection systems and identifies challenges in real-world deployment, usability, and user acceptance of emerging technologies.
Endangered Bird Species Classification Using Machine Learning TechniquesIRJET Journal
This document presents research on developing a machine learning model to classify endangered bird species using images. The researchers created a dataset of over 7,000 images from 20 endangered bird species and trained convolutional neural network (CNN) models on the data. They tested various hyperparameters and techniques, such as data augmentation, to improve the model's performance. Their best model achieved a promising accuracy of 98% on the test dataset. The researchers conclude that automated bird species identification using machine learning can help conservation efforts by aiding population monitoring and tracking, which supports endangered bird preservation.
Real Time Object Detection with Audio Feedback using Yolo v3ijtsrd
In this paper, we propose a system that combines real time object detection using the YOLOv3 algorithm with audio feedback to assist visually impaired individuals in locating and identifying objects in their surroundings. The YOLOv3 algorithm is a state of the art object detection algorithm that has been used in numerous studies for various applications. Audio feedback has also been studied in previous research as a useful tool for assisting visually impaired individuals. Our proposed system builds on the effectiveness of both these technologies to provide a valuable tool for improving the independence and quality of life of visually impaired individuals. We present the architecture of our proposed system, which includes a YOLOv3 model for object detection and a text to speech engine for providing audio feedback. We also present the results of our experiments, which demonstrate the effectiveness of our system in detecting and identifying objects in real time. Our proposed system can be used in various settings, such as indoor and outdoor environments, and can assist visually impaired individuals in various activities such as the navigation and object identification. Dr. K. Nagi Reddy | K. Sreeja | M. Sreenivasulu Reddy | K. Sireesha | M. Triveni "Real Time Object Detection with Audio Feedback using Yolo_v3" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-7 | Issue-2 , April 2023, URL: https://www.ijtsrd.com.com/papers/ijtsrd55158.pdf Paper URL: https://www.ijtsrd.com.com/engineering/electronics-and-communication-engineering/55158/real-time-object-detection-with-audio-feedback-using-yolov3/dr-k-nagi-reddy
RAILWAY-ELEPHANT CONFLICT MINIMISATION USING RADIO FREQUENCY TECHNOLOGYIRJET Journal
This document discusses the development of a system to detect elephants crossing railway tracks using radio frequency technology in order to minimize conflicts between elephants and trains in India. The system uses a YOLO model to detect elephants via camera monitoring the tracks. When an elephant is detected, radio frequency modules transmit signals to alert the nearby locomotive pilot and station master. The system also sends text messages and emails to notify the station master. The goal is to reduce accidents between elephants and trains by notifying train operators in time for them to stop or slow down if an elephant is spotted on the tracks.
This document presents research on developing an automated system for fish species detection using deep learning and the MobileNetV2 architecture. The researchers assembled a large dataset of fish photos and used MobileNetV2 for image classification. MobileNetV2 is efficient and effective for this task as it balances accuracy and computational performance. Through training and evaluation, the researchers demonstrated that their method achieves accurate fish species detection and categorization while maintaining computational efficiency compared to other techniques. Their proposed application aims to streamline aquatic ecosystem monitoring and conservation efforts by providing a precise and efficient means of assessing fish populations.
IRJET- A Leading Hand for the Blind –A ReviewIRJET Journal
This document reviews various technologies and devices that have been developed to assist visually impaired individuals in navigating and performing daily tasks. It discusses how advances in technologies like RFID, GPS, voice assistance, and image processing have enabled new discoveries to help the blind. The document then reviews several existing smart stick and navigation systems that use sensors like ultrasonic, infrared, and PIR along with technologies like GPS, GSM, Bluetooth and microcontrollers to guide and provide information to visually impaired users. However, many of these systems have limitations such as only working for predefined routes, inability to determine obstacle distances, or reliance on smartphone apps which may not always provide accurate information. Overall, the document examines the history and need for aids for the blind
Wildlife Identification using Object Detection using Computer Vision and YOLOIRJET Journal
This document discusses using the YOLO (You Only Look Once) algorithm for wildlife identification and monitoring through computer vision. YOLO is a real-time object detection framework that can efficiently process video frames to identify and track wildlife in order to provide insights about population dynamics, behaviors, and potential threats to support conservation efforts. The researchers trained the YOLO model on wildlife datasets to enable accurate recognition and classification of different species from CCTV camera feeds of wildlife habitats. The real-time capabilities of YOLO allow for continuous monitoring of wildlife populations and analysis of animal behaviors.
Anti-poaching System to Detect Poachers and Conserve Forest EcosystemIRJET Journal
This document proposes an anti-poaching system that uses sensors to detect poaching activity in forests and notify authorities. The system uses a cell phone detector sensor to detect signals from cell phones between 0.8-2.5GHz and trigger an alert with the phone's location. It also uses a PIR motion sensor with a range of 7-12 meters to detect intruders, then triggers a camera to take an image and send it along with location data via GPRS to a central server for authorities to monitor. The system is designed to be low-power, ruggedized and mounted in forests to automatically detect and report poaching activities to help conservation efforts.
Automatic detection of broiler’s feeding and aggressive behavior using you on...IAESIJAI
The high market demand for broiler chickens requires that chicken farmers improve their production performance. Production cost and poultry welfare are important competitiveness aspects in the poultry industry. To optimize these aspects, chicken behavior such as feeding and aggression needs to be observed continuously. However, this is not practically done entirely by humans. Implementation of precision live stock farming with deep learning can provide continuous, real-time and automated decisions. In this study, the you only look once version 4 (YOLOv4) architecture is used to detect feeding and aggressive chicken behavior. The data used includes 1,045 feeding bounding boxes and 753 aggressive bounding boxes. The model training is performed using the k-fold cross validation method. The best mean average precision (mAP) values obtained were 99.98% for eating behavior and 99.4% for aggressive behavior.
Automatic identification of animal using visual and motion saliencyeSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
IRJET- GPS Arduino based Tracking and Alarm System for Protection of Wildlife...IRJET Journal
This document describes a GPS-based tracking and alarm system to protect wildlife animals. The key components are a GPS module to track animal locations, a temperature sensor to monitor animal health, and RFID tags to identify individual animals. The system works as follows:
1) A GPS module tracks animal locations continuously and sends the data to an IoT platform.
2) A temperature sensor monitors each animal's temperature frequently and alerts if levels change.
3) RFID tags identify individual animals, and an RFID reader sounds an alarm if an animal crosses its boundary.
4) All sensor data on location, temperature, and animal ID are continuously updated on the IoT platform for remote monitoring without direct human involvement.
Automatic motion tracking system for analysis of insect behaviorWookjin Choi
Undergraduate research.
We present a multi-object tracking system to track small insects such as ants and bees. Motion-based object tracking recognizes the movements of objects in videos using information extracted from the given video frames. We applied several computer vision techniques, such as blob detection and appearance matching, to track ants. Moreover, we discussed different object detection methodologies and investigated the various challenges of object detection, such as illumination variations and blob merge/split. The proposed system effectively tracked multiple objects in various environments.
AUTOMATIC REAL-TIME RAILWAY FISHPLATE MONITORINGSYSTEM FOR EARLY WARNING USIN...IRJET Journal
This document describes an automatic real-time railway fishplate monitoring system using IoT to detect loosened fishplates and provide early warnings. The system uses proximity sensors to detect if fishplate bolts are loosened, an Arduino microcontroller to process the sensor data, a NodeMCU with WiFi to transmit data to the cloud, a GPS module to track the exact location of faults, and a mobile app to view fault locations and warnings. The system aims to reduce railway accidents by continuously and remotely monitoring the condition of fishplates. An experiment showed the system could successfully detect loosened bolts, track locations, and display warnings on a mobile app in real-time.
IRJET- Hybrid Approach to Reduce Energy Utilization in Wireless Sensor Networ...IRJET Journal
This document discusses using bio-inspired techniques to reduce energy utilization in wireless sensor networks. It begins by introducing wireless sensor networks and describing energy consumption as a major challenge. It then discusses several bio-inspired algorithms that could be applied for routing in wireless sensor networks, including ant colony optimization, artificial bee colony optimization, genetic algorithms, and particle swarm optimization. The document reviews related work applying these algorithms to optimize various wireless sensor network performance metrics like energy efficiency. It proposes developing a new routing algorithm based on swarm intelligence techniques to improve wireless sensor network performance.
Detection of Aedes aegypti larvae using single shot multibox detector with tr...journalBEEI
The flavivirus epidemiology has reached an alarming rate which haunts the world population including Malaysia. In fact, World Health Organization has proposed and practised many methods of vector control through environmental management, chemical and biological orientations but still cannot fully overcome the problem. This paper proposed a detection of Aedes Aegypti larvae in water storage tank using Single Shot Multibox Detector with transfer learning. The objective of the study was to acquire the training and the performance metrics of the detection. The detection was done using SSD with Inception_V2 through transfer learning. The experimental results revealed that the probability detection scored more than 80% accuracies and there was no false alarm. These results demonstrate the effectiveness of the model approach.
A Survey on Person Detection for Social Distancing and Safety Violation Alert...IRJET Journal
This document discusses methods for monitoring social distancing using video surveillance and deep learning techniques. It describes how faster R-CNN, single shot detector (SSD) and YOLO v3 deep learning models can be used to detect people in video frames and calculate the distance between individuals to determine if social distancing guidelines are being followed. If distances between people are found to be unsafe, the system can send alerts or cautions. The methodology is intended to help prevent the spread of COVID-19 by monitoring adherence to social distancing and triggering warnings if safety violations are detected.
Similar to Robust individual pig tracking (Keywords: Multi-object tracking, Performance evaluation, Pig detection, Pig localization, Pig tracking) (20)
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Advanced control scheme of doubly fed induction generator for wind turbine us...IJECEIAES
This paper describes a speed control device for generating electrical energy on an electricity network based on the doubly fed induction generator (DFIG) used for wind power conversion systems. At first, a double-fed induction generator model was constructed. A control law is formulated to govern the flow of energy between the stator of a DFIG and the energy network using three types of controllers: proportional integral (PI), sliding mode controller (SMC) and second order sliding mode controller (SOSMC). Their different results in terms of power reference tracking, reaction to unexpected speed fluctuations, sensitivity to perturbations, and resilience against machine parameter alterations are compared. MATLAB/Simulink was used to conduct the simulations for the preceding study. Multiple simulations have shown very satisfying results, and the investigations demonstrate the efficacy and power-enhancing capabilities of the suggested control system.
Neural network optimizer of proportional-integral-differential controller par...IJECEIAES
Wide application of proportional-integral-differential (PID)-regulator in industry requires constant improvement of methods of its parameters adjustment. The paper deals with the issues of optimization of PID-regulator parameters with the use of neural network technology methods. A methodology for choosing the architecture (structure) of neural network optimizer is proposed, which consists in determining the number of layers, the number of neurons in each layer, as well as the form and type of activation function. Algorithms of neural network training based on the application of the method of minimizing the mismatch between the regulated value and the target value are developed. The method of back propagation of gradients is proposed to select the optimal training rate of neurons of the neural network. The neural network optimizer, which is a superstructure of the linear PID controller, allows increasing the regulation accuracy from 0.23 to 0.09, thus reducing the power consumption from 65% to 53%. The results of the conducted experiments allow us to conclude that the created neural superstructure may well become a prototype of an automatic voltage regulator (AVR)-type industrial controller for tuning the parameters of the PID controller.
An improved modulation technique suitable for a three level flying capacitor ...IJECEIAES
This research paper introduces an innovative modulation technique for controlling a 3-level flying capacitor multilevel inverter (FCMLI), aiming to streamline the modulation process in contrast to conventional methods. The proposed
simplified modulation technique paves the way for more straightforward and
efficient control of multilevel inverters, enabling their widespread adoption and
integration into modern power electronic systems. Through the amalgamation of
sinusoidal pulse width modulation (SPWM) with a high-frequency square wave
pulse, this controlling technique attains energy equilibrium across the coupling
capacitor. The modulation scheme incorporates a simplified switching pattern
and a decreased count of voltage references, thereby simplifying the control
algorithm.
A review on features and methods of potential fishing zoneIJECEIAES
This review focuses on the importance of identifying potential fishing zones in seawater for sustainable fishing practices. It explores features like sea surface temperature (SST) and sea surface height (SSH), along with classification methods such as classifiers. The features like SST, SSH, and different classifiers used to classify the data, have been figured out in this review study. This study underscores the importance of examining potential fishing zones using advanced analytical techniques. It thoroughly explores the methodologies employed by researchers, covering both past and current approaches. The examination centers on data characteristics and the application of classification algorithms for classification of potential fishing zones. Furthermore, the prediction of potential fishing zones relies significantly on the effectiveness of classification algorithms. Previous research has assessed the performance of models like support vector machines, naïve Bayes, and artificial neural networks (ANN). In the previous result, the results of support vector machine (SVM) were 97.6% more accurate than naive Bayes's 94.2% to classify test data for fisheries classification. By considering the recent works in this area, several recommendations for future works are presented to further improve the performance of the potential fishing zone models, which is important to the fisheries community.
Electrical signal interference minimization using appropriate core material f...IJECEIAES
As demand for smaller, quicker, and more powerful devices rises, Moore's law is strictly followed. The industry has worked hard to make little devices that boost productivity. The goal is to optimize device density. Scientists are reducing connection delays to improve circuit performance. This helped them understand three-dimensional integrated circuit (3D IC) concepts, which stack active devices and create vertical connections to diminish latency and lower interconnects. Electrical involvement is a big worry with 3D integrates circuits. Researchers have developed and tested through silicon via (TSV) and substrates to decrease electrical wave involvement. This study illustrates a novel noise coupling reduction method using several electrical involvement models. A 22% drop in electrical involvement from wave-carrying to victim TSVs introduces this new paradigm and improves system performance even at higher THz frequencies.
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...IJECEIAES
Climate change's impact on the planet forced the United Nations and governments to promote green energies and electric transportation. The deployments of photovoltaic (PV) and electric vehicle (EV) systems gained stronger momentum due to their numerous advantages over fossil fuel types. The advantages go beyond sustainability to reach financial support and stability. The work in this paper introduces the hybrid system between PV and EV to support industrial and commercial plants. This paper covers the theoretical framework of the proposed hybrid system including the required equation to complete the cost analysis when PV and EV are present. In addition, the proposed design diagram which sets the priorities and requirements of the system is presented. The proposed approach allows setup to advance their power stability, especially during power outages. The presented information supports researchers and plant owners to complete the necessary analysis while promoting the deployment of clean energy. The result of a case study that represents a dairy milk farmer supports the theoretical works and highlights its advanced benefits to existing plants. The short return on investment of the proposed approach supports the paper's novelty approach for the sustainable electrical system. In addition, the proposed system allows for an isolated power setup without the need for a transmission line which enhances the safety of the electrical network
Bibliometric analysis highlighting the role of women in addressing climate ch...IJECEIAES
Fossil fuel consumption increased quickly, contributing to climate change
that is evident in unusual flooding and draughts, and global warming. Over
the past ten years, women's involvement in society has grown dramatically,
and they succeeded in playing a noticeable role in reducing climate change.
A bibliometric analysis of data from the last ten years has been carried out to
examine the role of women in addressing the climate change. The analysis's
findings discussed the relevant to the sustainable development goals (SDGs),
particularly SDG 7 and SDG 13. The results considered contributions made
by women in the various sectors while taking geographic dispersion into
account. The bibliometric analysis delves into topics including women's
leadership in environmental groups, their involvement in policymaking, their
contributions to sustainable development projects, and the influence of
gender diversity on attempts to mitigate climate change. This study's results
highlight how women have influenced policies and actions related to climate
change, point out areas of research deficiency and recommendations on how
to increase role of the women in addressing the climate change and
achieving sustainability. To achieve more successful results, this initiative
aims to highlight the significance of gender equality and encourage
inclusivity in climate change decision-making processes.
Voltage and frequency control of microgrid in presence of micro-turbine inter...IJECEIAES
The active and reactive load changes have a significant impact on voltage
and frequency. In this paper, in order to stabilize the microgrid (MG) against
load variations in islanding mode, the active and reactive power of all
distributed generators (DGs), including energy storage (battery), diesel
generator, and micro-turbine, are controlled. The micro-turbine generator is
connected to MG through a three-phase to three-phase matrix converter, and
the droop control method is applied for controlling the voltage and
frequency of MG. In addition, a method is introduced for voltage and
frequency control of micro-turbines in the transition state from gridconnected mode to islanding mode. A novel switching strategy of the matrix
converter is used for converting the high-frequency output voltage of the
micro-turbine to the grid-side frequency of the utility system. Moreover,
using the switching strategy, the low-order harmonics in the output current
and voltage are not produced, and consequently, the size of the output filter
would be reduced. In fact, the suggested control strategy is load-independent
and has no frequency conversion restrictions. The proposed approach for
voltage and frequency regulation demonstrates exceptional performance and
favorable response across various load alteration scenarios. The suggested
strategy is examined in several scenarios in the MG test systems, and the
simulation results are addressed.
Enhancing battery system identification: nonlinear autoregressive modeling fo...IJECEIAES
Precisely characterizing Li-ion batteries is essential for optimizing their
performance, enhancing safety, and prolonging their lifespan across various
applications, such as electric vehicles and renewable energy systems. This
article introduces an innovative nonlinear methodology for system
identification of a Li-ion battery, employing a nonlinear autoregressive with
exogenous inputs (NARX) model. The proposed approach integrates the
benefits of nonlinear modeling with the adaptability of the NARX structure,
facilitating a more comprehensive representation of the intricate
electrochemical processes within the battery. Experimental data collected
from a Li-ion battery operating under diverse scenarios are employed to
validate the effectiveness of the proposed methodology. The identified
NARX model exhibits superior accuracy in predicting the battery's behavior
compared to traditional linear models. This study underscores the
importance of accounting for nonlinearities in battery modeling, providing
insights into the intricate relationships between state-of-charge, voltage, and
current under dynamic conditions.
Smart grid deployment: from a bibliometric analysis to a surveyIJECEIAES
Smart grids are one of the last decades' innovations in electrical energy.
They bring relevant advantages compared to the traditional grid and
significant interest from the research community. Assessing the field's
evolution is essential to propose guidelines for facing new and future smart
grid challenges. In addition, knowing the main technologies involved in the
deployment of smart grids (SGs) is important to highlight possible
shortcomings that can be mitigated by developing new tools. This paper
contributes to the research trends mentioned above by focusing on two
objectives. First, a bibliometric analysis is presented to give an overview of
the current research level about smart grid deployment. Second, a survey of
the main technological approaches used for smart grid implementation and
their contributions are highlighted. To that effect, we searched the Web of
Science (WoS), and the Scopus databases. We obtained 5,663 documents
from WoS and 7,215 from Scopus on smart grid implementation or
deployment. With the extraction limitation in the Scopus database, 5,872 of
the 7,215 documents were extracted using a multi-step process. These two
datasets have been analyzed using a bibliometric tool called bibliometrix.
The main outputs are presented with some recommendations for future
research.
Use of analytical hierarchy process for selecting and prioritizing islanding ...IJECEIAES
One of the problems that are associated to power systems is islanding
condition, which must be rapidly and properly detected to prevent any
negative consequences on the system's protection, stability, and security.
This paper offers a thorough overview of several islanding detection
strategies, which are divided into two categories: classic approaches,
including local and remote approaches, and modern techniques, including
techniques based on signal processing and computational intelligence.
Additionally, each approach is compared and assessed based on several
factors, including implementation costs, non-detected zones, declining
power quality, and response times using the analytical hierarchy process
(AHP). The multi-criteria decision-making analysis shows that the overall
weight of passive methods (24.7%), active methods (7.8%), hybrid methods
(5.6%), remote methods (14.5%), signal processing-based methods (26.6%),
and computational intelligent-based methods (20.8%) based on the
comparison of all criteria together. Thus, it can be seen from the total weight
that hybrid approaches are the least suitable to be chosen, while signal
processing-based methods are the most appropriate islanding detection
method to be selected and implemented in power system with respect to the
aforementioned factors. Using Expert Choice software, the proposed
hierarchy model is studied and examined.
Enhancing of single-stage grid-connected photovoltaic system using fuzzy logi...IJECEIAES
The power generated by photovoltaic (PV) systems is influenced by
environmental factors. This variability hampers the control and utilization of
solar cells' peak output. In this study, a single-stage grid-connected PV
system is designed to enhance power quality. Our approach employs fuzzy
logic in the direct power control (DPC) of a three-phase voltage source
inverter (VSI), enabling seamless integration of the PV connected to the
grid. Additionally, a fuzzy logic-based maximum power point tracking
(MPPT) controller is adopted, which outperforms traditional methods like
incremental conductance (INC) in enhancing solar cell efficiency and
minimizing the response time. Moreover, the inverter's real-time active and
reactive power is directly managed to achieve a unity power factor (UPF).
The system's performance is assessed through MATLAB/Simulink
implementation, showing marked improvement over conventional methods,
particularly in steady-state and varying weather conditions. For solar
irradiances of 500 and 1,000 W/m2
, the results show that the proposed
method reduces the total harmonic distortion (THD) of the injected current
to the grid by approximately 46% and 38% compared to conventional
methods, respectively. Furthermore, we compare the simulation results with
IEEE standards to evaluate the system's grid compatibility.
Enhancing photovoltaic system maximum power point tracking with fuzzy logic-b...IJECEIAES
Photovoltaic systems have emerged as a promising energy resource that
caters to the future needs of society, owing to their renewable, inexhaustible,
and cost-free nature. The power output of these systems relies on solar cell
radiation and temperature. In order to mitigate the dependence on
atmospheric conditions and enhance power tracking, a conventional
approach has been improved by integrating various methods. To optimize
the generation of electricity from solar systems, the maximum power point
tracking (MPPT) technique is employed. To overcome limitations such as
steady-state voltage oscillations and improve transient response, two
traditional MPPT methods, namely fuzzy logic controller (FLC) and perturb
and observe (P&O), have been modified. This research paper aims to
simulate and validate the step size of the proposed modified P&O and FLC
techniques within the MPPT algorithm using MATLAB/Simulink for
efficient power tracking in photovoltaic systems.
Adaptive synchronous sliding control for a robot manipulator based on neural ...IJECEIAES
Robot manipulators have become important equipment in production lines, medical fields, and transportation. Improving the quality of trajectory tracking for
robot hands is always an attractive topic in the research community. This is a
challenging problem because robot manipulators are complex nonlinear systems
and are often subject to fluctuations in loads and external disturbances. This
article proposes an adaptive synchronous sliding control scheme to improve trajectory tracking performance for a robot manipulator. The proposed controller
ensures that the positions of the joints track the desired trajectory, synchronize
the errors, and significantly reduces chattering. First, the synchronous tracking
errors and synchronous sliding surfaces are presented. Second, the synchronous
tracking error dynamics are determined. Third, a robust adaptive control law is
designed,the unknown components of the model are estimated online by the neural network, and the parameters of the switching elements are selected by fuzzy
logic. The built algorithm ensures that the tracking and approximation errors
are ultimately uniformly bounded (UUB). Finally, the effectiveness of the constructed algorithm is demonstrated through simulation and experimental results.
Simulation and experimental results show that the proposed controller is effective with small synchronous tracking errors, and the chattering phenomenon is
significantly reduced.
Remote field-programmable gate array laboratory for signal acquisition and de...IJECEIAES
A remote laboratory utilizing field-programmable gate array (FPGA) technologies enhances students’ learning experience anywhere and anytime in embedded system design. Existing remote laboratories prioritize hardware access and visual feedback for observing board behavior after programming, neglecting comprehensive debugging tools to resolve errors that require internal signal acquisition. This paper proposes a novel remote embeddedsystem design approach targeting FPGA technologies that are fully interactive via a web-based platform. Our solution provides FPGA board access and debugging capabilities beyond the visual feedback provided by existing remote laboratories. We implemented a lab module that allows users to seamlessly incorporate into their FPGA design. The module minimizes hardware resource utilization while enabling the acquisition of a large number of data samples from the signal during the experiments by adaptively compressing the signal prior to data transmission. The results demonstrate an average compression ratio of 2.90 across three benchmark signals, indicating efficient signal acquisition and effective debugging and analysis. This method allows users to acquire more data samples than conventional methods. The proposed lab allows students to remotely test and debug their designs, bridging the gap between theory and practice in embedded system design.
Detecting and resolving feature envy through automated machine learning and m...IJECEIAES
Efficiently identifying and resolving code smells enhances software project quality. This paper presents a novel solution, utilizing automated machine learning (AutoML) techniques, to detect code smells and apply move method refactoring. By evaluating code metrics before and after refactoring, we assessed its impact on coupling, complexity, and cohesion. Key contributions of this research include a unique dataset for code smell classification and the development of models using AutoGluon for optimal performance. Furthermore, the study identifies the top 20 influential features in classifying feature envy, a well-known code smell, stemming from excessive reliance on external classes. We also explored how move method refactoring addresses feature envy, revealing reduced coupling and complexity, and improved cohesion, ultimately enhancing code quality. In summary, this research offers an empirical, data-driven approach, integrating AutoML and move method refactoring to optimize software project quality. Insights gained shed light on the benefits of refactoring on code quality and the significance of specific features in detecting feature envy. Future research can expand to explore additional refactoring techniques and a broader range of code metrics, advancing software engineering practices and standards.
Smart monitoring technique for solar cell systems using internet of things ba...IJECEIAES
Rapidly and remotely monitoring and receiving the solar cell systems status parameters, solar irradiance, temperature, and humidity, are critical issues in enhancement their efficiency. Hence, in the present article an improved smart prototype of internet of things (IoT) technique based on embedded system through NodeMCU ESP8266 (ESP-12E) was carried out experimentally. Three different regions at Egypt; Luxor, Cairo, and El-Beheira cities were chosen to study their solar irradiance profile, temperature, and humidity by the proposed IoT system. The monitoring data of solar irradiance, temperature, and humidity were live visualized directly by Ubidots through hypertext transfer protocol (HTTP) protocol. The measured solar power radiation in Luxor, Cairo, and El-Beheira ranged between 216-1000, 245-958, and 187-692 W/m 2 respectively during the solar day. The accuracy and rapidity of obtaining monitoring results using the proposed IoT system made it a strong candidate for application in monitoring solar cell systems. On the other hand, the obtained solar power radiation results of the three considered regions strongly candidate Luxor and Cairo as suitable places to build up a solar cells system station rather than El-Beheira.
An efficient security framework for intrusion detection and prevention in int...IJECEIAES
Over the past few years, the internet of things (IoT) has advanced to connect billions of smart devices to improve quality of life. However, anomalies or malicious intrusions pose several security loopholes, leading to performance degradation and threat to data security in IoT operations. Thereby, IoT security systems must keep an eye on and restrict unwanted events from occurring in the IoT network. Recently, various technical solutions based on machine learning (ML) models have been derived towards identifying and restricting unwanted events in IoT. However, most ML-based approaches are prone to miss-classification due to inappropriate feature selection. Additionally, most ML approaches applied to intrusion detection and prevention consider supervised learning, which requires a large amount of labeled data to be trained. Consequently, such complex datasets are impossible to source in a large network like IoT. To address this problem, this proposed study introduces an efficient learning mechanism to strengthen the IoT security aspects. The proposed algorithm incorporates supervised and unsupervised approaches to improve the learning models for intrusion detection and mitigation. Compared with the related works, the experimental outcome shows that the model performs well in a benchmark dataset. It accomplishes an improved detection accuracy of approximately 99.21%.
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesChristina Lin
Traditionally, dealing with real-time data pipelines has involved significant overhead, even for straightforward tasks like data transformation or masking. However, in this talk, we’ll venture into the dynamic realm of WebAssembly (WASM) and discover how it can revolutionize the creation of stateless streaming pipelines within a Kafka (Redpanda) broker. These pipelines are adept at managing low-latency, high-data-volume scenarios.
Comparative analysis between traditional aquaponics and reconstructed aquapon...bijceesjournal
The aquaponic system of planting is a method that does not require soil usage. It is a method that only needs water, fish, lava rocks (a substitute for soil), and plants. Aquaponic systems are sustainable and environmentally friendly. Its use not only helps to plant in small spaces but also helps reduce artificial chemical use and minimizes excess water use, as aquaponics consumes 90% less water than soil-based gardening. The study applied a descriptive and experimental design to assess and compare conventional and reconstructed aquaponic methods for reproducing tomatoes. The researchers created an observation checklist to determine the significant factors of the study. The study aims to determine the significant difference between traditional aquaponics and reconstructed aquaponics systems propagating tomatoes in terms of height, weight, girth, and number of fruits. The reconstructed aquaponics system’s higher growth yield results in a much more nourished crop than the traditional aquaponics system. It is superior in its number of fruits, height, weight, and girth measurement. Moreover, the reconstructed aquaponics system is proven to eliminate all the hindrances present in the traditional aquaponics system, which are overcrowding of fish, algae growth, pest problems, contaminated water, and dead fish.
Understanding Inductive Bias in Machine LearningSUTEJAS
This presentation explores the concept of inductive bias in machine learning. It explains how algorithms come with built-in assumptions and preferences that guide the learning process. You'll learn about the different types of inductive bias and how they can impact the performance and generalizability of machine learning models.
The presentation also covers the positive and negative aspects of inductive bias, along with strategies for mitigating potential drawbacks. We'll explore examples of how bias manifests in algorithms like neural networks and decision trees.
By understanding inductive bias, you can gain valuable insights into how machine learning models work and make informed decisions when building and deploying them.
TIME DIVISION MULTIPLEXING TECHNIQUE FOR COMMUNICATION SYSTEMHODECEDSIET
Time Division Multiplexing (TDM) is a method of transmitting multiple signals over a single communication channel by dividing the signal into many segments, each having a very short duration of time. These time slots are then allocated to different data streams, allowing multiple signals to share the same transmission medium efficiently. TDM is widely used in telecommunications and data communication systems.
### How TDM Works
1. **Time Slots Allocation**: The core principle of TDM is to assign distinct time slots to each signal. During each time slot, the respective signal is transmitted, and then the process repeats cyclically. For example, if there are four signals to be transmitted, the TDM cycle will divide time into four slots, each assigned to one signal.
2. **Synchronization**: Synchronization is crucial in TDM systems to ensure that the signals are correctly aligned with their respective time slots. Both the transmitter and receiver must be synchronized to avoid any overlap or loss of data. This synchronization is typically maintained by a clock signal that ensures time slots are accurately aligned.
3. **Frame Structure**: TDM data is organized into frames, where each frame consists of a set of time slots. Each frame is repeated at regular intervals, ensuring continuous transmission of data streams. The frame structure helps in managing the data streams and maintaining the synchronization between the transmitter and receiver.
4. **Multiplexer and Demultiplexer**: At the transmitting end, a multiplexer combines multiple input signals into a single composite signal by assigning each signal to a specific time slot. At the receiving end, a demultiplexer separates the composite signal back into individual signals based on their respective time slots.
### Types of TDM
1. **Synchronous TDM**: In synchronous TDM, time slots are pre-assigned to each signal, regardless of whether the signal has data to transmit or not. This can lead to inefficiencies if some time slots remain empty due to the absence of data.
2. **Asynchronous TDM (or Statistical TDM)**: Asynchronous TDM addresses the inefficiencies of synchronous TDM by allocating time slots dynamically based on the presence of data. Time slots are assigned only when there is data to transmit, which optimizes the use of the communication channel.
### Applications of TDM
- **Telecommunications**: TDM is extensively used in telecommunication systems, such as in T1 and E1 lines, where multiple telephone calls are transmitted over a single line by assigning each call to a specific time slot.
- **Digital Audio and Video Broadcasting**: TDM is used in broadcasting systems to transmit multiple audio or video streams over a single channel, ensuring efficient use of bandwidth.
- **Computer Networks**: TDM is used in network protocols and systems to manage the transmission of data from multiple sources over a single network medium.
### Advantages of TDM
- **Efficient Use of Bandwidth**: TDM all
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
A review on techniques and modelling methodologies used for checking electrom...nooriasukmaningtyas
The proper function of the integrated circuit (IC) in an inhibiting electromagnetic environment has always been a serious concern throughout the decades of revolution in the world of electronics, from disjunct devices to today’s integrated circuit technology, where billions of transistors are combined on a single chip. The automotive industry and smart vehicles in particular, are confronting design issues such as being prone to electromagnetic interference (EMI). Electronic control devices calculate incorrect outputs because of EMI and sensors give misleading values which can prove fatal in case of automotives. In this paper, the authors have non exhaustively tried to review research work concerned with the investigation of EMI in ICs and prediction of this EMI using various modelling methodologies and measurement setups.
Literature Review Basics and Understanding Reference Management.pptxDr Ramhari Poudyal
Three-day training on academic research focuses on analytical tools at United Technical College, supported by the University Grant Commission, Nepal. 24-26 May 2024
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELgerogepatton
As digital technology becomes more deeply embedded in power systems, protecting the communication
networks of Smart Grids (SG) has emerged as a critical concern. Distributed Network Protocol 3 (DNP3)
represents a multi-tiered application layer protocol extensively utilized in Supervisory Control and Data
Acquisition (SCADA)-based smart grids to facilitate real-time data gathering and control functionalities.
Robust Intrusion Detection Systems (IDS) are necessary for early threat detection and mitigation because
of the interconnection of these networks, which makes them vulnerable to a variety of cyberattacks. To
solve this issue, this paper develops a hybrid Deep Learning (DL) model specifically designed for intrusion
detection in smart grids. The proposed approach is a combination of the Convolutional Neural Network
(CNN) and the Long-Short-Term Memory algorithms (LSTM). We employed a recent intrusion detection
dataset (DNP3), which focuses on unauthorized commands and Denial of Service (DoS) cyberattacks, to
train and test our model. The results of our experiments show that our CNN-LSTM method is much better
at finding smart grid intrusions than other deep learning algorithms used for classification. In addition,
our proposed approach improves accuracy, precision, recall, and F1 score, achieving a high detection
accuracy rate of 99.50%.
Introduction- e - waste – definition - sources of e-waste– hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste management– e-waste handling rules - waste minimization techniques for managing e-waste – recycling of e-waste - disposal treatment methods of e- waste – mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste – E-waste in India- case studies.
1. International Journal of Electrical and Computer Engineering (IJECE)
Vol. 14, No. 1, February 2024, pp. 279~293
ISSN: 2088-8708, DOI: 10.11591/ijece.v14i1.pp279-293 279
Journal homepage: http://ijece.iaescore.com
Robust individual pig tracking
Aggaluck Jaoukaew, Watcharapan Suwansantisuk, Pinit Kumhom
Department of Electronic and Telecommunication Engineering, King Mongkut’s University of Technology Thonburi, Bangkok,
Thailand
Article Info ABSTRACT
Article history:
Received Jun 23, 2023
Revised Jul 16, 2023
Accepted Jul 17, 2023
The locations of pigs in the group housing enable activity monitoring and
improve animal welfare. Vision-based methods for tracking individual pigs
are noninvasive but have low tracking accuracy owing to long-term pig
occlusion. In this study, we developed a vision-based method that accurately
tracked individual pigs in group housing. We prepared and labeled datasets
taken from an actual pig farm, trained a faster region-based convolutional
neural network to recognize pigs’ bodies and heads, and tracked individual
pigs across video frames. To quantify the tracking performance, we
compared the proposed method with the global optimization (GO) method
with the cost function and the simple online and real-time tracking (SORT)
method on four additional test datasets that we prepared, labeled, and made
publicly available. The predictive model detects pigs’ bodies accurately,
with F1-scores of 0.75 to 1.00, on the four test datasets. The proposed
method achieves the largest multi-object tracking accuracy (MOTA) values
at 0.75, 0.98, and 1.00 for three test datasets. In the remaining dataset, the
proposed method has the second-highest MOTA of 0.73. The proposed
tracking method is robust to long-term occlusion, outperforms the
competitive baselines in most datasets, and has practical utility in helping to
track individual pigs accurately.
Keywords:
Multi-object tracking
Performance evaluation
Pig detection
Pig localization
Pig tracking
This is an open access article under the CC BY-SA license.
Corresponding Author:
Watcharapan Suwansantisuk
Department of Electronic and Telecommunication Engineering, King Mongkut’s University of Technology
Thonburi
126 Pracha Uthit Road, Thung Khru, Bangkok 10140, Thailand
Email: watcharapan.suw@kmutt.ac.th
1. INTRODUCTION
The global pig industry is valued at US$ 254 billion in 2022 and is estimated to reach US$ 418
billion by 2028 [1]. In commercial farming, pigs are raised in closed pens and are subjected to stress and
illness. Pig locations across time can reveal the pigs’ activities and well-being [2]–[8] and enable a farm to
detect a disease early [9]–[14]. The accurate tracking of individual pigs benefits the billion-dollar industry.
The tracking of individual farm pigs is challenging. Pigs of similar size and age were raised in the
same pen to manage their growth [10]. However, similar pigs are difficult to differentiate and track
individually [3]. In addition, the outline shape of a pig changes according to the pig’s activity. A dynamic
shape complicates a vision-based tracker, which identifies an object as a pig based on it is appearance.
Finally, the trajectory of the pig was random. Two pigs that meet momentarily may depart in unpredictable
directions and cause the tracker to switch the pigs’ identities incorrectly. Individual pig tracking aims to
accurately detect and track each pig over time. Detection accuracy is commonly measured by the false
positive ratio (FPR), false negative ratio (FNR), precision, recall, and F1-score. Tracking accuracy is
commonly measured by FPR, FNR, mostly tracked trajectory (MTT), number of identity switches (NIS), and
2. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 1, February 2024: 279-293
280
multi-object tracking accuracy (MOTA) [15]–[19]. To be accurate, a tracker must overcome appearance
similarity, dynamic pig shape, and random pig movement.
Tracking individual pigs can be handled using the framework of multi-object tracking (MOT) [18]–[23],
which is divided into invasive and noninvasive methods. Invasive methods implant a unique radio frequency
identification (RFID) tag or place a specific mark on an animal, and install an RFID reader to interrogate tags
or a video camera to capture the marks [24], [25]. For farms that place distinct ear tags on the pigs, a previous
study [24] applies a convolutional network to recognize the tags and track individual pigs. RFID and marks
increase the tracking accuracy and reduce identity switching. However, they disturb animals and become
futile if tags or marks are detached from the animals [26]. Noninvasive methods require the installation of
one or more video cameras in a pen to identify and localize individual pigs in each video frame and track the
pigs over time [15], [27]–[29]. The locations of the pigs are relative to the pixel coordinates and, if needed,
can be transformed into the physical coordinates of the pen. If the video processing and the tracking occur at
a centralized unit, a large amount of video data can be compressed using convolutional neural networks
(CNN) [30] or other techniques before transmission. Noninvasive methods minimize animal suffering and
can be applied to large farms. Considering animal welfare, noninvasive methods are appealing.
Several variations of noninvasive methods exist for tracking pigs and other animals. In [15], a
fingerprinting technique was proposed that mitigates identification (ID) switching in unmarked individual fish
during their interaction and grouping. The fingerprinting technique uses both the position and direction of the
fish to confirm its identity. The fish’s position is extracted from the background, whereas the fish’s direction is
extracted from a style of motion including exclusion, occlusion, and interaction. The tracking method is
appropriate for fishes and animals that occlude one another for a short duration, but is unsuitable for pigs, which
engage in long-term occlusion. To cope with occlusion, the method [31] automatically and dynamically builds
representations that enable the robust and effective tracking of animals. This method uses a Gaussian mixture
model and expectation maximization for background subtraction and tracking, respectively. Images for this
method must conform to a specific color model, namely the YUV color model, which separates the luminance
component (Y) from the two chrominance components (U and V). The YUV color model with appropriate
lighting control is required to minimize false negatives during background subtraction. Without lighting control,
this method faces the problem of disconnected foreground blobs for a single object. More importantly, the
method is efficient only when the animals have simple shapes and move in regular motion patterns. This
method is unsuitable for pigs with complex shapes. To address illumination changes, long-term occlusion, and
ID switching, a study [32] developed a collaborative tracking algorithm to track multiple objects in the presence
of inter-occlusion using a color-based particle filter. The position of each detected object is represented by a
blob, that is, a rectangular bounding box, which is used to build the tracker model. The distance between the
blobs is used to determine the type of occlusion, including overlapping, partial occlusion, and full occlusion. An
appropriate tracking method was selected based on the occlusion type. A drawback of this method is that it
requires several complex algorithms to deal with multiple tasks. To develop a tracking method that is simple,
and robust to illumination changes and long-term occlusions, machine learning approaches are used to detect
animals or objects of interest in video frames. Common methods include faster region-based convolutional
neural network (faster R-CNN) [33]–[38], you only look once (YOLO) [39]–[43], single-shot multi-box
detector (SSD) [44]–[47], and feature pyramid network (FPN) [48]–[51]. After training with a dataset, these
methods recognize the external appearance of an object or animal of interest, and predict the blob position, size,
and boundary of each animal. In [43], YOLOX-S and YOLO v5s detectors have been used in detecting and
classifying pig activities. In [36], the Faster R-CNN model was applied to automatically localize individual pigs
from a side-view video and track them in a situation where, owing to a detection error, some pigs were lost from
a video frame. Faster R-CNN can process frames at a speed of 0.2 sec per frame [36]. With this speed, faster R-
CNN achieves near real-time detection and is attractive.
Although much work has been done on animal and pig tracking, existing work is fundamentally
limited. The previous work constructed a rectangular bounding box around a pig and represented the pig’s
location by the centroid of the box. As two pigs are nearby and aligned diagonally, the centroid of a bounding
box for one pig may be located on the body of another pig, leading to ID switching after the two pigs depart.
A new method that resolves these limitations will increase tracking accuracy.
In this paper, we propose a method that tracks individual pigs and is robust to long-term occlusions.
We prepared datasets and trained a faster R-CNN to recognize pigs in a farm environment. The model detects
the pigs’ bodies and heads in each video frame and differs from existing models that detect a combination of
the body and head as one unit. The proposed method represents each pig’s location using a bounding box
around the pig’s body, as opposed to a single centroid in the existing work. The enlarged representation of
the location alleviates ID switching. We evaluated the performance of the proposed tracking method against
state-of-the-art methods and found that the proposed method outperformed existing methods. The main
contributions are the following:
3. Int J Elec & Comp Eng ISSN: 2088-8708
Robust individual pig tracking (Aggaluck Jaoukaew)
281
− Labeled datasets, which are publicly available [52] to measure the accuracy of pig detection and tracking.
− An individual-pig tracking method, which is robust to a long-term pig-to-pig occlusion.
− Performance evaluation of the proposed method, showing superior performance compared to state-of-the-
art methods.
The proposed method can detect and track pigs accurately, even for pigs in an environment different from
that used in training the predictive model. These contributions may improve farm practices and pig welfare.
The remainder of this paper is organized: section 2 describes the problem statement, the dataset for
training a pig-recognition model, and the proposed pig-tracking method. Section 3 describes the datasets for
testing the model, evaluates the performance of the proposed method for detection and tracking, discusses the
results, and suggests future research directions. Section 4 concludes the paper and summarizes important
findings.
2. METHOD
The research method entails problem formulation (subsection 2.1), preparation of the training
dataset (subsection 2.2), and design of the tracking method (subsections 2.3–2.5). As an overview, the
proposed pig-tracking method identifies the head and body of each pig in video frames using a faster R-CNN
model specifically trained for pig recognition. The proposed method matches the bounding boxes over the
pigs’ bodies across frames and repeats the matching for the bounding boxes over the heads of the pigs.
Finally, it matches the body and head of the pig in each frame. Each part of the research method is described
in detail below.
2.1. Problem statement
The system model is illustrated in Figure 1. The pen is closed, has a video camera attached to the
ceiling, and contains N pigs of similar size and appearance. The video camera provides K frames of
red-green-blue (RGB) images, denoted by F [1..K], for pig tracking. Each frame contains all N pigs, possibly
with pig-to-pig occlusions. The multi-tracking system takes video frames F [1..K] as input, detects, and
tracks individual pigs in video frames. The output is a unique identifier, i, of each pig, where 1≤i ≤N, and the
bounding box with respect to the pixel coordinates in each frame of the ith identified pig. Our aim is to
design a method to track individual pigs accurately.
Figure 1. A system to track individual pigs takes a video as an input
2.2. Training a model
To train a model to recognize pigs’ bodies and heads, we prepared a training video dataset. The
videos were taken from a 2×2 square-meter pen consisting of N=10 pigs. The breed of the eight pigs was a
mix of Landrace and Large White. The breed of the two pigs was a mix of Duroc and Hamshire. Each pig
weighed 8-16 kg. Training videos were collected in the morning, noon, and afternoon with 696 video frames
in total, covering different activities and lighting conditions.
To identify an object as a pig, we manually annotated the pig’s head and body boundaries in the
video frames using the Pascal Visual Object Classes Challenge 2007 as shown in Figure 2. Pigs that are
heavily occluded are not annotated to improve boundary detection. The annotated head and body boundaries
4. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 1, February 2024: 279-293
282
assume a rectangular shape parallel to the image sides and cover the major head and body areas. For pigs that
are oriented in roughly the same direction, the length and width of their boundaries are labeled as
approximately the same size. This approach helps improve the accuracy of faster R-CNN boundary detection.
In our prepared dataset, the total number of bounding boxes over either the head or body is approximately
6,500, a large quantity, coming from 10 pigs/image×696 images, subtracted by the number of heads and the
number of bodies, respectively, that are heavily occluded.
Figure 2. Video frames were labelled and used for training a neural network to recognize pigs’ bodies and
heads
Seventy percent of the 696 images were used for training the faster R-CNN model, while the 30%
remaining images were used for testing the model. In the training stage, the learning rate was set to 0.0002
and the batch size was set to 1. The learning rate was small and appropriate because when pigs stayed in a
group, their appearances were similar. The batch size can be increased to suit the computing power of the
training machine. In the training and testing stages, the lost value obtained from 200,000 rounds of
processing was used to determine the accuracy of the generated faster R-CNN model. We use appropriate
parameters to train the model.
2.3. Tracking algorithm
The tracking algorithm is shown in Algorithm 1. The algorithm uses video frames F [1..K] and the
number N of pigs as inputs, where F [k] denotes the image at the kth video frame for 1≤k≤K. The output was
an array D[1..N, kst..K] of structures, where D[n, k] contains information about the bounding boxes over the
head and body of pig n in frame k. Line 1 applies the faster R-CNN model to predict the boundaries 𝐵body
and 𝐵head around the pigs’ bodies and heads, respectively. The variables 𝐵body [1..M, 1..K], 𝐵head [1..M,
1..K], nˆbody[1..K], and nˆhead[1..K] are arrays, where M is the maximum number of detectable pigs in video
frames. For a given frame 1≤k≤K, the variables nˆbody[k] and nˆhead[k] are the numbers of detected pigs’ bodies
and heads, respectively, in the kth video frame. Variable 𝐵body [n, k] is the structure of the bounding boxes
over the body of the nth detectable pig in the kth video frame, where 1≤n≤nˆbody[k]; and variable 𝐵head [n, k]
is the analogous structure over the pig’s head, where 1≤n≤nˆbody[k]. Structures 𝐵body [n, k] and 𝐵head [n, k]
contain the points (xmin, ymin) in the upper-left corner, (xmax, ymax) in the lower-right corner, and (cx, cy)
in the centroid of the bounding box. Line 2 determines the index kst of the first video frame that contains N
pigs’ bodies and N pigs’ heads. We consider that the number of frames is sufficiently large such that kst exists.
5. Int J Elec & Comp Eng ISSN: 2088-8708
Robust individual pig tracking (Aggaluck Jaoukaew)
283
Algorithm 1. Individual pig tracking
Input: F[1..K], N
Output: D[1..N, kst..K]
1: (Bbody, nˆbody, Bhead, nˆhead)=Faster-R-CNN(F)
2: kst=the minimum index such that both nˆbody[kst] and nˆhead[kst] equal N
3: (Cbody, Chead)=BlobRepairing(Bbody, nˆbody, Bhead, nˆhead, kst)
4: match=Body-Head Matching(Cbody, Chead, kst)
5: Initialize D[n, k] to contain information of the body Cbody[n, k] and
head Chead[match[n, k], k], for each kst≤k≤K and 1≤n≤N
Next, the algorithm calls the method of blob repair, which maps the bodies of the same pig across
different frames to the same identification number and maps the heads of the same pig across different frames
to the same identification number. The output variables 𝐶body [1..N, kst..K] and 𝐶head [1..N, kst..K] are arrays of
structures containing information about the bodies and heads, respectively, of N pigs in each frame, starting
from the kstth frame to the last frame. Fields of structures 𝐶body [n, k] and 𝐶head [n, k] are (xmin, ymin),
(xmax, ymax), (cx, cy), and a new field id, which is the unique identification of the pig’s body and head,
respectively. For flexibility in blob repair, the unique identification of the pig’s body may differ from that of
the pig’s head, even though they identify the same pig. This discrepancy will be resolved in the next step, line
4, which matches the identification number of the pig’s body to the corresponding identification number of the
pig’s head for the same pig. Finally, line 5 consolidates the body and head of the same pig into the same unit
and outputs array D[1..N, kst..K] of structures. The structure D[n, k] contains the body and head positions in
frame k of the pig, whose unique identification is n. This algorithm terminates and completes the tracking task.
2.4. Blob repairing
Body-blob repair aims to match a pig’s body in a given frame with the corresponding pig’s body in
the next frame. Head-blob repair aims to perform analogous matching for pigs’ heads. See Figure 3 for an
illustration. The word “repairing” emphasizes the most important step in body-to-body and head-to-head
matching: to repair a lost body blob, a lost head blob, an excessive body blob, and an excessing head blob.
Blob repairing matches either the heads or the bodies across different frames.
Figure 3. Blob repairing maps body and head blobs among consecutive frames, shown for N=3 pigs. The
lines indicate body or head blobs that belong to the same pig
The proposed method of blob repair appears in algorithm 2 and is based on the following ideas.
First, the start frame, that is, the kstth frame, has N head blobs and N body blobs by construction, and has
already been repaired. Blob repairing progressively matches pigs’ bodies and heads in a current frame, k,
with the bodies and heads in the previous frame, k-1, for kst+1≤k≤K. Second, if the number of body blobs in
the current frame does not equal N, pigs in the current frame must be heavily occluded so that the faster
R-CNN model either fails to detect or excessively detects a pig’s body. In this case, the body blobs in the
current frame are unreliable. Blob repairing will equate the positions of the pigs’ bodies and heads in the
current frame to those in the previous frame. See lines 3 and 4 of Algorithm 2. Third, if the number of body
blobs in the current frame is N, the body blob in the current frame is matched to the nearest body blob in the
previous frame. In line 8 of the algorithm, the notion of “nearest” is measured by the average displacement
between the bounding-box coordinates:
𝑓(𝑛, 𝑗, 𝑘) =
1
4
∑ (𝐵𝑏𝑜𝑑𝑦[𝑛, 𝑘]. 𝑠 − 𝐵𝑏𝑜𝑑𝑦[𝑗, 𝑘 − 1]. 𝑠 )
𝑠 (1)
6. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 1, February 2024: 279-293
284
where the summation index s covers fields s {xmin, ymin, xmax, ymax}. In the algorithm, the set of
unmatched indices is stored in variable U, which initially equals a full set {1, 2, 3 ..., N} and is reduced by
one element at a time to the empty set-in lines 6-12. Fourth, the number of detectable pigs’ heads in the
current frame may differ from that in the previous frame. Blob repairing matches pigs’ heads in the previous
frame with the nearest ones in the current frame. Here, the notation of “nearest” for pigs’ heads is the
distance between the centroids of the bounding boxes (line 15 of the algorithm).
𝑔(𝑛, 𝑗, 𝑘) = √∑ (𝐵head[𝑛, 𝑘]. 𝑡 − 𝐵head[𝑗, 𝑘 − 1]. 𝑡)2
𝑡 (2)
The summation index t covers fields t {cx, cy}. Using different measures f and g for the body and head
blobs is appropriate because the pig’s body may be rotated within the blob, making the centroid an unfit
representation of the body’s blob position. In addition, the pigs’ heads are smaller than their bodies and will
not rotate much within the blob, making a centroid a suitable choice to capture the head position. Fifth, if the
number of detectable pigs’ heads in the current frame is smaller than that of the previous frame, the
unmatched head blobs and their identities in the previous frame are copied to the current frame, as shown in
lines 20-24. On the other hand, if the number of detectable pigs’ heads in the current frame is larger than that
of the previous frame, the unmatched head blobs and their identities in the current frame are discarded. The
outputs of the algorithms are arrays 𝐶body [1..N, 1..K] and 𝐶head [1..N, 1..K], where 𝐶body [n, k] and 𝐶head [n,
k] are the structures of the nth blob for the pig’s body and head, respectively, at the kth frame, where 1≤n≤N
and kst≤k≤K.
Algorithm 2. Blob repairing
Input: Bbody[1..M, 1..K], nˆbody[1..K], Bhead[1..M, 1..K], nˆhead[1..K], kst
Output: Cbody[1..N, kst..K], Chead[1..N, kst..K]
1: Initialize Cbody[n, kst]= Bbody[n, kst], Cbody[n, kst].id=n, Chead[n, kst]=Bbody[n, kst],
and Chead[n, kst].id=n, for each 1≤n≤N
2: for k=kst+1 to K do
3: if nˆbody=N then
4: Initialize Cbody[n, k]= Cbody[n, k−1] and Chead[n, k]=Chead[n, k−1], for each
1≤n≤N
5: else
6: U={ 1, 2, 3, . . . , N }
7: for n=1 to N do
8: J=arg minj∈U f(i, j, k)
9: Cbody[n, k]=Bbody[n, k]
10: Cbody[n, k].id= Cbody[J, k−1].id
11: U=U{ J }
12: end for
13: V={1, 2, 3, . . . , nˆhead[k]}
14: for n=1 to nˆhead[k−1] do
15: J=arg minj∈V g(n, j, k)
16: Chead[J, k]=Bhead[J, k]
17: Chead[J, k].id=Chead[n, k−1].id
18: V=V{ J }
19: end for
20: m=N−nˆhead[k]
21: if nˆhead[k]<N then
22: Let j1, j2, . . . , jm denote the elements of V
23: Chead[nˆhead[k]+i, k]=Chead[ji, k], for each 1≤i≤m
24: end if
25: end if
26: end for
2.5. Matching of pig’s body to it is head
The matching stage aims to match a body’s blob to a head’s blob in the same frame such that the
same pig has it is body and head paired together. The key idea in the proposed matching is to examine the
intersection of union (IoU) as well as to minimize the distance between the head and body’s blobs. The top
three IoU values are used to find the head blob with the closest distance to the body blob. Next, we describe
the algorithm used for the matching stage in detail.
The algorithm for the matching stage appears in algorithm 3 and is illustrated in Figure 4. The inputs
are the index of the start frame kst, and arrays 𝐶body and 𝐶head of structures, containing information about the
body’s blobs and head’s blobs. The output is an array match [1..N, 1..K] of integers to indicate the matching.
For each frame k, the value of match [n, k]=j indicates that the body blob 𝐶body [n, k] and the head blob 𝐶head
[j, k] belong to the same pig. The algorithm matching the body’s blobs and head’s blobs in the same frame is
7. Int J Elec & Comp Eng ISSN: 2088-8708
Robust individual pig tracking (Aggaluck Jaoukaew)
285
shown in lines 1–33. The index of the frame under matching is denoted by variable k, which runs from kst to
K, as shown in line 1. The inner loop of the algorithm iterates through variable i, which is the index of the
body’s blob and ranges from 1 to N, as shown in lines 2–32. In line 5, set U of unmatched head indices is
initialized to equal a full set {1, 2, 3, . . . , N }. Lines 6–9 calculate the value of IoU from each pair of blobs
of the body and head. The three largest IoUs, namely IoU[j1]≥IoU[j2]≥IoU[j3], were selected for further
matching, as shown in line 10. If frame k is the start frame, the matching is based only on IoU[j1] because the
minimum distance to the previous frame is unavailable, as shown in lines 14–16. In line 14, the index of the
already-matched head is removed from set U. For a subsequent frame k>kst, the distances of the head’s blobs
in the current and previous frames are considered, as presented in lines 17–19. Figure 4(a) illustrates the pigs
in the previous frame, where the bodies have already been matched to the heads. The distance between the
head’s blobs in the current and previous frames is calculated. Figure 4(b) illustrates the pigs in the current
frame, where each pig’s body is to be matched based on the distance with a head. The distances under
consideration have three values stored in variables dist1, dist2 and dist3, where
distℓ = √∑ (𝐶head[jlast, 𝑘 − 1]. 𝑢 − 𝐶head[𝑗ℓ, 𝑘]. 𝑢)2
𝑢 (3)
for u {xmin, xmax} and ℓ=1, 2, 3. All three values are further compared to determine the closest distance
based on the three conditions presented in lines 21-30. In the first condition, if dist1 is smaller than both dist2
and dist3, then index j1 is matched with the body’s blob at index i, and the already-matched index j1 is
removed from set U. The second and third conditions are for cases where dist2 and dist3, respectively, are the
minima among the three distances. Figure 4(c) is an example of a pig’s head that best matches the pig’s body
under consideration. After the algorithm finds the best body-to-head matching, a single ID is assigned to the
body and head blobs of the same pig, as shown in Figure 4(d). Overall, the algorithm processes each frame
and maps the IDs of the body and head blobs.
Algorithm 3. Body-head matching
Input: kst, Chead, Cbody
Output: match[1..N, 1..K] array of integers to indicate the index of the head
that matches to the index of the body
1: for k=kst to K do
2: for n=1 to N do
3: Initialize IoU[j]=0, for each j=1, 2, 3, . . ., K
4: body=rectangle with the corners (Cbody[n, k].xmin, Cbody[n, k].ymin) and
(Cbody[n, k].xmax, Cbody[n, k].ymax)
5: U={ 1, 2, 3, . . . , N }
6: for j=1 to N do
7: head=rectangle with the corners at (Chead[j, k].xmin, Chead[j, k].ymin)
and (Chead[j, k].xmax, Chead[j, k].ymax)
8: IoU[j]=area(body ⋂ head)/area( body ⋃ head)
9: end for
10: Pick the indices j1, j2, j3 such that j1 ∈ U, j2 ∈ U, j3 ∈ U, and
IoU[j1]≥IoU[j2]≥IoU[j3]>0 are the three largest positive IoUs
11: if (cannot find such j1, j2, j3) then
12: Unable to match the head-and-body for this frame. Go to line 1
for the next value of k
13: end if
14: if (k equals kst) then
15: match [n, k]=j1
16: U=U{j1}
17: else
18: jlast=match[n, k–1]
19: Calculate distℓ according to (3) for ℓ=1, 2, 3
20: distmin=min {distℓ:ℓ=1, 2, 3}
21: if distmin=dist1 then
22: match[n, k]=j1
23: U=U{j1}
24: else if distmin=dist2 then
25: match[n, k]=j2
26: U=U{ j2 }
27: else
28: match[n, k]=j3
29: U=U{j3}
30: end if
31: end if
32: end for
33:end for
8. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 1, February 2024: 279-293
286
(a) (b)
(c) (d)
Figure 4. The matching stage (a) considers the previous frame, (b) selects each body bounding box in the
current frame, (c) matches the body to a head, and (d) assigns the same ID to the matching head and body
3. RESULTS AND DISCUSSION
To evaluate the performance of the proposed tracking method, we took steps to ensure fairness.
First, we prepared test datasets that were disjointed from the dataset used in section 2.2 for training the
pig-detection model. Then, we evaluated the performance of the proposed detection model and the proposed
pig tracking method on the test datasets.
3.1. Test datasets
We prepared four datasets (Videos 1-4) to evaluate the pig identification and tracking methods.
Each video contained 10 frames, down-sampled from 5,000 continuous frames, of pigs of the same number
and mixed breads. Videos 1-3 were captured in the morning, midday, and evening, respectively. The pig,
pen, and camera setup in videos 1-3 are the same as those in the videos used in training the Faster R-CNN
model (section 2.2). Video 4 has a different camera setup, pen, and pigs from the video used in training the
Faster R-CNN model. Videos 1-3 were taken from an environment familiar to the pig detection model, while
video 4 was not.
Table 1 lists the characteristics of the datasets used for the pig detection. A different time of the day
leads to a different pig behavior and the occlusion ratio (OR), which measures the degree to which a pig’s
part overlaps with the same part of another pig. The head OR equals
∑ 𝑑𝑘
𝐾
𝑘=1
∑ 𝑛𝑘
𝐾
𝑘=1
where dk is the number of pigs’
heads that overlap with the heads of any other pig in frame k, and nk=N is the total number of pigs in frame k.
The body OR is defined similarly, but on the pigs’ bodies. The higher the OR, the greater the overlap, and the
more difficult it is to detect a pig. The body-to-body OR is largest at 0.40 on video 2, because at noon, pigs
tend to lay down, rest, and cause body-to-body occlusion. Videos 1-4 test the abilities of the detection and
tracking methods under various conditions. We made the test datasets available to other researchers [52].
9. Int J Elec & Comp Eng ISSN: 2088-8708
Robust individual pig tracking (Aggaluck Jaoukaew)
287
Table 1. Test datasets consist of four videos of different characteristics (bbox=bounding box)
Dataset Capturing Environment Head Body
# of bboxes OR # of bboxes OR
VDO 1 Morning on familiar pen and pigs 100 0.04 100 0.26
VDO 2 Midday on familiar pen and pigs 100 0.13 100 0.40
VDO 3 Afternoon on familiar pen and pigs 100 0.12 100 0.24
VDO 4 Afternoon on unfamiliar pen and pigs 100 0.06 100 0.22
3.2. Performance metrics
We considered six performance metrics for pig detection: true positive ratio (TPR), FPR, FNR,
precision, recall, and F1-score. In addition, we considered six performance metrics for pig tracking: TPR,
FPR, FNR, MTT, NIS, and MOTA. The performance metrics for detection and tracking were obtained from
the predicted bounding boxes and ground truth, without human intervention, for reproducibility. In this
section, we describe the method to obtain these performance metrics.
During detection, in a given video frame f, the ground truth bounding boxes g1, g2, . . . , gN are
matched with the predicted bounding boxes p1, p2, . . . , pn, where n is the number of predicted bounding
boxes in frame f. The matching method is the greedy maximum-weight bipartite-graph matching, where the
two disjoint sets of vertices are {g1, g2, . . . , gN} and {p1, p2, . . ., pn}. The weight wi,j between vertices gi and
pj favors, first, the IoU and, second, the centroid between bounding boxes. In particular, wi,j is a tuple (ai,j, bi,j)
where ai,j is the IoU between gi and pj, if the IoU is ≥0.6; and ai,j is zero, otherwise. The element bi,j is the
distance between the centroids of the bounding boxes gi and pj. An IoU threshold of 0.6 is suitable, meaning
that the two bounding boxes are significantly overlapped [36]. A comparison between the two weights begins
with the IoU comparison and, in the case of a tie, is settled by the distance comparison. Following the greedy
implementation, we repeatedly add an edge to the matching, starting from the maximum-weighted edge to a
smaller-weighted edge, as long as the added edge preserves bipartite matching. The matching process
establishes the pairs (gi, pm(i)) between the ground truth and the predicted bounding box, where m(i) is the
corresponding matched vertex. After the matching, true positive (TP), false positive (FP), FN are obtained
from the IoU between each bounding-box pair (gi, pm(i)), using standard definitions of these metrics [53],
where the IoU threshold is set to 0.6. TPR, FPR, and FNR are the ratios of TP, FP, and FN, respectively, to
the number of ground truth bounding boxes, which is 100 as shown in Table 1. Maximum matching ensures
that the TPR is at the largest possible value, and that the FPR and FNR are the smallest. The TPR, FPR, and
FNR in the detection can serve as the ultimate limits for the analogous tracking metrics.
To evaluate the tracking performance, we rearranged the predicted pig IDs to match those in the
ground truths; and then evaluated the TP, FP, FN, MTT, and NIS. The step to rearrange the predicted pig IDs
ensures fairness because the tracker and ground truth may name the same pig by two different numbers
consistently through the video frames. Matching occurs between the predicted bounding boxes and the
ground truth at the earliest ground-truth video frame where the predicted model detects all N pigs. The
matching is the greedy maximum-weight bipartite-graph matching with the same weight construction used by
the detection metrics. Having N predicted pigs means that the matching is perfect: every pig’s predicted ID is
matched to a unique ground-truth pig ID. The predicted pig IDs were renamed to match the ground truth IDs.
After perfect matching, the ground truth bounding box gi and predicted bounding pi for the same
index i are deemed to identify the same pig. Then, the TP, FP, and FN are obtained in each frame using the
standard definitions of these metrics [53], with an IoU threshold of 0.6. In computing the MTT, the predicted
trajectory of a given pig is considered mostly tracked if 80% of the predicted bounding boxes significantly
overlap with the ground truths. Again, the two boxes overlap significantly if their IoU is ≥0.6 [36]. To obtain
an NIS for a test video, we sum the NISs of the individual pigs. For example, Table 2 contains the predicted
pig IDs, the NIS for each pig, and the NIS for video 1 and the proposed tracker. To obtain an NIS of a given
pig, we match the pig’s predicted bounding boxes to the ground-truth’s bounding boxes in each ground-truth
video frame, using the greedy maximum-weight bipartite-graph matching; and count the number of ID
switches. Finally, MOTA is obtained from 1–x [36], where x is the ratio between the sum of FP, FN, and NIS
to the sum of the total ground truth bounding boxes and the maximum possible NIS value. The total number
of ground-truth bounding boxes is MN, and the maximum possible NIS value is (M-1)N, where M=10 is the
total number of ground-truth frames as shown in Table 1. The method for computing the detection and
tracking metrics is appropriate.
3.3. Detection evaluation
Figure 5 shows examples of bounding boxes that were generated by our model to detect the heads
and bodies of pigs. Images of pigs in subfigures 5(a)–5(d) are taken from videos 1 to 4, respectively, and
show a group of pigs in similar positions. A green bounding box is the detected pig’s body, while a cyan box
10. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 1, February 2024: 279-293
288
is the detected pig’s head. The proposed method accurately detects pigs’ bodies even when the pigs are
congregated in a group and experience pig-to-pig occlusion. Detecting a pig’s head is more difficult than
detecting a pig’s body. In Figure 5(d), video 4 contains mistakes in head detection: two bounding boxes
intended for pigs’ heads appear at the buttocks; and one bounding box is missing from the pig’s head. Visual
inspection showed that the proposed pig detection model made few mistakes and performed well in these
video frames.
Table 2. To obtain the NIS, predicted pig IDs are matched to ground-truth’s, shown for video 1 and the
proposed tracker. The ID of zero means that the tracker loses track of a pig
Ground-truth frame Ground-truth pig ID
1 2 3 4 5 6 7 8 9 10
500 1 2 3 4 5 6 7 8 9 10
1,000 1 2 3 4 5 6 7 8 9 10
1,500 1 2 3 8 5 6 7 4 9 10
2,000 7 2 3 8 5 6 1 4 9 10
2,500 7 2 3 8 5 6 1 4 9 10
3,000 7 0 0 8 5 6 1 4 9 10
3,500 7 3 0 8 5 6 1 4 9 10
4,000 7 8 3 0 5 6 1 4 9 10
4,500 7 8 3 4 5 6 1 0 9 10
5,000 7 0 3 8 5 6 1 4 9 10
NIS for each pig 1 4 2 4 0 0 1 3 0 0
Sum=NIS 15
(a) (b)
(c) (d)
Figure 5. The bounding boxes cover the detected pigs’ bodies and heads, shown as an example for frames
taken from (a) VDO1, (b) VDO2, (c) VDO3, and (d) VDO4
11. Int J Elec & Comp Eng ISSN: 2088-8708
Robust individual pig tracking (Aggaluck Jaoukaew)
289
Table 3 shows the overall detection performance of the pigs’ heads and bodies. The ORs reported in
Table 1 affect the FPR and FNR of pig detection. A high OR tends to lead to an error in boundary detection
and, hence, a large FPR. The FNR is zero because the predictive model outputs N bounding boxes for heads
and bodies, although some bounding boxes are not at the correction positions, and hence a non-zero FPR.
The different lighting conditions in videos 1-3 did not significantly affect the F1-score, showing the
robustness of the detection model to the lighting condition. The precision, recall, and F1-score for body
detection are generally larger than those for head detection. For example, in video 3, the F1-scores are 0.99
on body detection and 0.83 on head detection. Furthermore, for unfamiliar video 4, the F1-score for body
detection had the best value of 1.00, whereas the F1-score for head detection was 0.29. Bodies are larger and
hence easier to detect than heads. The proposed algorithm appropriately uses the bodies of pigs for tracking.
Table 3. Detecting the pigs’ bodies is more accurate than detecting the pigs’ heads (Prec.=Precision)
Part Dataset TPR FPR FNR Prec. Recall F1
Body VDO1 0.94 0.06 0.00 0.94 1.00 0.97
VDO2 0.95 0.05 0.00 0.95 1.00 0.97
VDO3 0.99 0.01 0.00 0.99 1.00 0.99
VDO4 1.00 0.00 0.00 1.00 1.00 1.00
Head VDO1 0.78 0.22 0.00 0.78 1.00 0.88
VDO2 0.72 0.28 0.00 0.72 1.00 0.84
VDO3 0.71 0.29 0.00 0.71 1.00 0.83
VDO4 0.17 0.83 0.00 0.17 1.00 0.29
Table 4. In tracking, the proposed method outperforms the state-of-the-art methods in most test datasets
Dataset Method TPR FPR FNR MTT NIS MOTA
VDO1 Proposed
SORT
GO
0.64
0.90
0.55
0.36
0.00
0.45
0.00
0.10
0.00
5
10
4
15
20
23
0.73
0.84
0.66
VDO2 Proposed
SORT
GO
0.70
0.63
0.53
0.30
0.27
0.47
0.00
0.10
0.00
5
4
3
18
23
36
0.75
0.68
0.58
VDO3 Proposed
SORT
GO
0.99
0.92
0.77
0.01
0.08
0.23
0.00
0.00
0.00
10
8
6
2
3
22
0.98
0.94
0.78
VDO4 Proposed
SORT
GO
1.00
0.82
0.05
0.00
0.18
0.95
0.00
0.00
0.00
10
8
0
0
2
34
1.00
0.89
0.34
3.4. Tracking evaluation
We compared the proposed method with the state-of-the-art methods [17], [36] which track moving
animals of a similar appearance without lighting control. The global optimization (GO) method in [17] is a
deterministic method using the Hungarian algorithm, whereas the simple online and real-time tracking
(SORT) method in [36] is a probabilistic method using a combined Hungarian algorithm and Kalman filter.
The existing methods are competitive trackers.
The results of the individual pig tracking are shown in Table 4, where the best performance for each
metric is indicated in bold. The FNRs of the proposed method and the GO method are zero for every test
video, while the FNRs of the SORT method are 0.10 for videos 1-2 and 0.0 for videos 3-4. The proposed and
GO methods track all N pigs in each video frame, while the SORT method fails to track 10% of the pigs, i.e.,
10 out of the 100 pigs in total as shown in Table 1, in either video 1 or video 2. With a large FPR and a small
FPR, the proposed method places correct bounding boxes on the areas where the pigs of the intended IDs are
located. The TPR of the proposed methods are 0.70, 0.99, and 1.00, which are the largest values in test videos
2, 3, and 4, respectively. In Video 1, the TPR of the proposed method is 0.64, which is the second largest
value after the TPR of 0.90, achieved by the SORT method. The overall tracking accuracy was captured by
MOTA. The proposed method has the largest MOTAs in three out of four test videos and a perfect MOTA of
1.00 in video 4. The proposed method performs exceptionally well on video 4, which contains different pigs
in a different pen from those used by the Faster R-CNN. The exceptional performance indicates that the
proposed method is a robust pig tracker in an unfamiliar environment. The proposed method outperformed
the state-of-the-art methods for most videos.
In the GO method, tracking pigs from their heads is inaccurate. As shown in Table 3, detecting a
pig’s head is more difficult than detecting a pig’s body, which is confirmed by the low TPR of head
detection. For example, in Video 4, the TPR for detecting the pigs’ heads was 0.17. If the pigs must be both
detected and tracked, the tracking TPR will not exceed 0.17. In Table 4, the tracking TPR of the GO method
12. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 1, February 2024: 279-293
290
was 0.05, which is ≤0.17. The detection TPRs in Table 3 are the upper bounds of the tracking TPRs. As
shown in Table 4, tracking pigs by their bodies, as in the proposed and SORT methods, generally
outperforms tracking the pigs by their heads.
Figures 6 and 7 are examples of the trajectories obtained from fine manually labeled ground truth
(dashed line) and the various trackers (solid lines) on selected pigs and videos. The x- and y-axes are the
image x- and y-coordinates in pixels. The trajectories of the ground truth, proposed, and SORT methods are
taken from the centroids of the pig’s bodies. On the other hand, the trajectory of the GO method is from the
centroids of the pig’s heads. The proposed method tracks a pig accurately in Figures 6(a) and 7(a), as the
ground truth’s trajectories agree with the trajectories produced by the proposed method. A broken line on the
trajectory indicates a loss of tracking, which contributes to a false negative (FN). A sharp transition on the
trajectory indicates an unusual pig’s movement and is caused by ID switches. The proposed method does not
have a tracking loss on these exemplary trajectories. In contrast, the SORT method suffers from a tracking
loss in Figures 6(b) and 7(b). The tracking loss of pig ID 4 in either Figure 6(b) or Figure 7(b) does not
contradict the FNR of 0.00 in Table 4 for the SORT method on Videos 3-4, because the FNR in Table 4 is the
average of the FNRs of N pigs and is rounded to two decimal places, due to the 100 available ground-truth
frames in the test datasets. Furthermore, the GO method has a low tracking accuracy and produces a
trajectory that is far from the ground truth. A discrepancy comes from ID switches, i.e., a different pig was
tracked in Figure 6(c) (also observed in Figures 6(b) and 7(c)), and from an error in the positions of the head
bounding boxes in Figure 7(c). A poor trajectory in Figure 7(c) is consistent with a large FPR of head
detection on video 4 as shown in Table 3. Indeed in Table 4, the GO method has an MTT of zero; it does not
track any trajectory correctly for any pig on 100 ground-truth frames as shown in Table 1. The proposed
method is the most accurate tracker.
(a) (b) (c)
Figure 6. The trajectories of pig ID 6 on test Video 3 show that (a) the proposed method is most accurate than
(b) the SORT and (c) GO methods
(a) (b) (c)
Figure 7. The trajectories of pig ID 4 on test video 4 show that (a) the proposed method is most accurate than
(b) the SORT and (c) GO methods
0 200 400 600 800
image x-coordinate (pixel)
0
200
400
600
800
image
y-coordinate
(pixel)
Ground truth
Proposed
0 200 400 600 800
image x-coordinate (pixel)
0
200
400
600
800
image
y-coordinate
(pixel)
Ground truth
SORT
0 200 400 600 800
image x-coordinate (pixel)
0
200
400
600
800
image
y-coordinate
(pixel)
Ground truth
GO
0 200 400 600 800 1000 1200
image x-coordinate (pixel)
0
200
400
600
800
1000
1200
image
y-coordinate
(pixel)
Ground truth
Proposed
0 200 400 600 800 1000 1200
image x-coordinate (pixel)
0
200
400
600
800
1000
1200
image
y-coordinate
(pixel)
Ground truth
SORT
0 200 400 600 800 1000 1200
image x-coordinate (pixel)
0
200
400
600
800
1000
1200
image
y-coordinate
(pixel)
Ground truth
GO
13. Int J Elec & Comp Eng ISSN: 2088-8708
Robust individual pig tracking (Aggaluck Jaoukaew)
291
Several factors play a role in increasing the tracking accuracy of the proposed method. The proposed
method uses a rectangle to mark the boundary of each pig. In contrast, existing methods mark each pig by
using its centroid alone. As a pig moves, its centroid may become closer to one another and cause an ID
switch. A rectangular boundary captures a larger portion of the body and is more robust to ID switching.
These advantages improved the tracking performance of the proposed method.
There are several directions to extend this research. The proposed method for pig tracking is
sufficiently general to be applied to other animals, provided that the animal’s head can be distinguished from
its body. Future research can entail tracking other animals that have great economic, societal, or cultural
importance. In addition, the process of head matching and body matching can be achieved simultaneously
across several frames, as opposed to being done on each pair of adjacent frames. To reduce the complexity of
the matching, a metaheuristic algorithm such as the giant trevally optimizer (GTO) [54] can be applied.
Moreover, the number of animals in each pen was fixed and known in this study. Future research may cover
unknown or changing numbers of animals. Finally, future research can use knowledge of the animal’s
tracked location as a feature to determine its activity. These future studies will extend the proposed tracking
method to a broader context.
4. CONCLUSION
Farm animals living in closed pens have high opportunities to fight or be injured. Individual pig
tracking can increase animal welfare and provide a basis for behavioral monitoring and disorder diagnosis.
However, individual pig tracking is difficult to achieve accurately because of the similarity in pig appearance
and the tendency of pigs to remain in a group and create an occlusion. A method that can accurately track
individual pigs has an advantage for animals and farm owners.
Using a top-view video, this study developed a method to track each pig in a realistic farm
environment. To detect pigs in a given video, we created and labeled a dataset of pigs on an actual farm and
trained a Faster R-CNN to recognize an object as a pig. The key idea in dataset preparation is to label only
the visible pigs to increase detection accuracy. To evaluate the performance of the proposed detection
method, we tested the model on separate videos and found that detection performance increased significantly
when the pigs’ bodies were used for identification. This finding matches the intuition that the pig’s body
occupies a large portion and serves to better identify a pig. The developed model detected pigs well across all
test videos and stipulated that the body was the main feature for pig identification.
The proposed tracking method builds on the strength of the pig detection model and specific
tracking ideas. The position of a pig in the next frame is difficult to forecast. To mitigate this difficulty, the
proposed method detects both the head and body of each pig and uses only the frames in which the pig under
consideration is detectable. Furthermore, to improve tracking accuracy, the proposed method uses a
rectangle, as opposed to a centroid, to locate each pig. The proposed method is superior to state-of-the-art
methods, namely, the SORT and GO methods. The identity of an individual pig can be tracked, even in the
case of pig-to-pig occlusion. Given this advantage, the complete trajectory of each pig can be obtained and
used for behavior monitoring, pig activity classification, and disease detection.
ACKNOWLEDGEMENTS
This work is supported in part by the Research Strengthening Project of the Faculty of Engineering,
King Mongkut’s University of Technology Thonburi.
REFERENCES
[1] “Global pork market, size, global forecast 2023-2028, industry trends, growth, share, outlook impact of inflation, opportunity
company analysis,” Research and Markets, 2023. https://www.researchandmarkets.com/report/pork (accessed Apr. 07, 2023).
[2] M. A. Kashiha et al., “Automatic monitoring of pig locomotion using image analysis,” Livestock Science, vol. 159, pp. 141–148,
Jan. 2014, doi: 10.1016/j.livsci.2013.11.007.
[3] S. Ott et al., “Automated video analysis of pig activity at pen level highly correlates to human observations of behavioural
activities,” Livestock Science, vol. 160, pp. 132–137, Feb. 2014, doi: 10.1016/j.livsci.2013.12.011.
[4] C. Munsterhjelm, M. Heinonen, and A. Valros, “Effects of clinical lameness and tail biting lesions on voluntary feed intake in
growing pigs,” Livestock Science, vol. 181, pp. 210–219, Nov. 2015, doi: 10.1016/j.livsci.2015.09.003.
[5] S. G. Matthews, A. L. Miller, T. PlÖtz, and I. Kyriazakis, “Automated tracking to measure behavioural changes in pigs for health
and welfare monitoring,” Scientific Reports, vol. 7, no. 1, Dec. 2017, doi: 10.1038/s41598-017-17451-6.
[6] R. B. D’Eath et al., “Automatic early warning of tail biting in pigs: 3D cameras can detect lowered tail posture before an
outbreak,” Plos One, vol. 13, no. 4, Apr. 2018, doi: 10.1371/journal.pone.0194524.
[7] A. Alameer et al., “Automated detection and quantification of contact behaviour in pigs using deep learning,” Biosystems
Engineering, vol. 224, pp. 118–130, Dec. 2022, doi: 10.1016/j.biosystemseng.2022.10.002.
[8] F. Hakansson and D. B. Jensen, “Automatic monitoring and detection of tail-biting behavior in groups of pigs using video-based
deep learning methods,” Frontiers in Veterinary Science, vol. 9, Jan. 2023, doi: 10.3389/fvets.2022.1099347.
14. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 1, February 2024: 279-293
292
[9] I. Kyriazakis and J. Houdijk, “Food intake and performance of pigs during health, disease and recovery,” Paradigms in pig
science, pp. 493–513, 2007.
[10] E. Fernández-Carrión, M. Martínez-Avilés, B. Ivorra, B. Martínez-López, Á. M. Ramos, and J. M. Sánchez-Vizcaíno, “Motion-
based video monitoring for early detection of livestock diseases: The case of African swine fever,” Plos One, vol. 12, no. 9, Sep.
2017, doi: 10.1371/journal.pone.0183793.
[11] P. Statham, L. Green, M. Bichard, and M. Mendl, “Predicting tail-biting from behaviour of pigs prior to outbreaks,” Applied
Animal Behaviour Science, vol. 121, no. 3–4, pp. 157–164, Dec. 2009, doi: 10.1016/j.applanim.2009.09.011.
[12] Y. Seddon, “Development of improved disease monitoring tools and management strategies to promote health in finishing pigs,”
Newcastle University, 2011.
[13] M. H. Rostagno, S. D. Eicher, and D. C. Lay, “Immunological, physiological, and behavioral effects of salmonella enterica
carriage and shedding in experimentally infected finishing pigs,” Foodborne Pathogens and Disease, vol. 8, no. 5, pp. 623–630,
May 2011, doi: 10.1089/fpd.2010.0735.
[14] S. T. Ahmed, H.-S. Mun, H. Yoe, and C.-J. Yang, “Monitoring of behavior using a video-recording system for recognition of
Salmonella infection in experimentally infected growing pigs,” Animal, vol. 9, no. 1, pp. 115–121, 2015, doi:
10.1017/S1751731114002213.
[15] A. Pérez-Escudero, J. Vicente-Page, R. C. Hinz, S. Arganda, and G. G. de Polavieja, “idTracker: tracking individuals in a group
by automatic identification of unmarked animals,” Nature Methods, vol. 11, no. 7, pp. 743–748, Jul. 2014, doi:
10.1038/nmeth.2994.
[16] W. Luo, J. Xing, A. Milan, X. Zhang, W. Liu, and T.-K. Kim, “Multiple object tracking: A literature review,” Artificial
Intelligence, vol. 293, Apr. 2021, doi: 10.1016/j.artint.2020.103448.
[17] M. Wang, M. L. V Larsen, D. Liu, J. F. M. Winters, J.-L. Rault, and T. Norton, “Towards re-identification for long-term tracking
of group housed pigs,” Biosystems Engineering, vol. 222, pp. 71–81, Oct. 2022, doi: 10.1016/j.biosystemseng.2022.07.017.
[18] L. Zhang, H. Gray, X. Ye, L. Collins, and N. Allinson, “Automatic individual pig detection and tracking in pig farms,” Sensors,
vol. 19, no. 5, Mar. 2019, doi: 10.3390/s19051188.
[19] M. Wutke et al., “Detecting animal contacts-a deep learning-based pig detection and tracking approach for the quantification of
social contacts,” Sensors, vol. 21, no. 22, Nov. 2021, doi: 10.3390/s21227512.
[20] M. Kashiha et al., “Automatic identification of marked pigs in a pen using image pattern recognition,” Computers and Electronics
in Agriculture, vol. 93, pp. 111–120, Apr. 2013, doi: 10.1016/j.compag.2013.01.013.
[21] Q. Guo et al., “Enhanced camera-based individual pig detection and tracking for smart pig farms,” Computers and Electronics in
Agriculture, vol. 211, Aug. 2023, doi: 10.1016/j.compag.2023.108009.
[22] M. Mittek, E. T. Psota, J. D. Carlson, L. C. Pérez, T. Schmidt, and B. Mote, “Tracking of group‐housed pigs using multi‐ellipsoid
expectation maximisation,” IET Computer Vision, vol. 12, no. 2, pp. 121–128, Mar. 2018, doi: 10.1049/iet-cvi.2017.0085.
[23] E. Psota, M. Mittek, L. Pérez, T. Schmidt, and B. Mote, “Multi-pig part detection and association with a fully-convolutional
network,” Sensors, vol. 19, no. 4, Feb. 2019, doi: 10.3390/s19040852.
[24] E. T. Psota, T. Schmidt, B. Mote, and L. C. Pérez, “Long-term tracking of group-housed livestock using keypoint detection and
MAP estimation for individual animal identification,” Sensors, vol. 20, no. 13, Jun. 2020, doi: 10.3390/s20133670.
[25] L. E. van der Zande, O. Guzhva, and T. B. Rodenburg, “Individual detection and tracking of group housed pigs in their home pen
using computer vision,” Frontiers in Animal Science, vol. 2, Apr. 2021, doi: 10.3389/fanim.2021.669312.
[26] E. Leslie, M. Hernández-Jover, R. Newman, and P. Holyoake, “Assessment of acute pain experienced by piglets from ear tagging,
ear notching and intraperitoneal injectable transponders,” Applied Animal Behaviour Science, vol. 127, no. 3–4, pp. 86–95, Nov.
2010, doi: 10.1016/j.applanim.2010.09.006.
[27] N. M. Lind, M. Vinther, R. P. Hemmingsen, and A. K. Hansen, “Validation of a digital video tracking system for recording pig
locomotor behaviour,” Journal of Neuroscience Methods, vol. 143, no. 2, pp. 123–132, 2005, doi: 10.1016/j.jneumeth.2004.09.019.
[28] B. T. Morris and M. M. Trivedi, “A survey of vision-based trajectory learning and analysis for surveillance,” IEEE Transactions
on Circuits and Systems for Video Technology, vol. 18, no. 8, pp. 1114–1127, Aug. 2008, doi: 10.1109/TCSVT.2008.927109.
[29] T. Fukunaga, S. Kubota, S. Oda, and W. Iwasaki, “GroupTracker: Video tracking system for multiple animals under severe
occlusion,” Computational Biology and Chemistry, vol. 57, pp. 39–45, Aug. 2015, doi: 10.1016/j.compbiolchem.2015.02.006.
[30] H. T. Sadeeq, T. H. Hameed, A. S. Abdi, and A. N. Abdulfatah, “Image compression using neural networks: a review,”
International Journal of Online and Biomedical Engineering (iJOE), vol. 17, no. 14, pp. 135–153, Dec. 2021, doi:
10.3991/ijoe.v17i14.26059.
[31] V. Papadourakis and A. Argyros, “Multiple objects tracking in the presence of long-term occlusions,” Computer Vision and
Image Understanding, vol. 114, no. 7, pp. 835–846, Jul. 2010, doi: 10.1016/j.cviu.2010.02.003.
[32] J. Xiao and M. Oussalah, “Collaborative tracking for multiple objects in the presence of inter-occlusions,” IEEE Transactions on
Circuits and Systems for Video Technology, vol. 26, no. 2, pp. 304–318, Feb. 2016, doi: 10.1109/TCSVT.2015.2406193.
[33] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: towards real-time object detection with region proposal networks,” IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137–1149, Jun. 2017, doi:
10.1109/TPAMI.2016.2577031.
[34] M.-C. Roh and J. Lee, “Refining faster-RCNN for accurate object detection,” in 2017 Fifteenth IAPR International Conference on
Machine Vision Applications (MVA), May 2017, pp. 514–517, doi: 10.23919/MVA.2017.7986913.
[35] H. Jiang and E. Learned-Miller, “Face detection with the faster R-CNN,” in 12th IEEE International Conference on Automatic
Face and Gesture Recognition (FG 2017), May 2017, pp. 650–657, doi: 10.1109/FG.2017.82.
[36] J. Cowton, I. Kyriazakis, and J. Bacardit, “Automated individual pig localisation, tracking and behaviour metric extraction using
deep learning,” IEEE Access, vol. 7, pp. 108049–108060, 2019, doi: 10.1109/ACCESS.2019.2933060.
[37] K. Srijakkot, I. Kanjanasurat, N. Wiriyakrieng, and C. Benjangkaprasert, “The comparison of Faster R-CNN and Atrous Faster R-
CNN in different distance and light condition,” Journal of Physics: Conference Series, vol. 1457, no. 1, Jan. 2020, doi:
10.1088/1742-6596/1457/1/012015.
[38] D. Avola et al., “MS-Faster R-CNN: multi-stream backbone for improved faster R-CNN object detection and aerial tracking from
UAV images,” Remote Sensing, vol. 13, no. 9, Apr. 2021, doi: 10.3390/rs13091670.
[39] M. Ju et al., “A kinect-based segmentation of touching-pigs for real-time monitoring,” Sensors, vol. 18, no. 6, May 2018, doi:
10.3390/s18061746.
[40] A. Alameer, I. Kyriazakis, and J. Bacardit, “Automated recognition of postures and drinking behaviour for the detection of
compromised health in pigs,” Scientific Reports, vol. 10, no. 1, Aug. 2020, doi: 10.1038/s41598-020-70688-6.
[41] A. Bhujel, E. Arulmozhi, B.-E. Moon, and H.-T. Kim, “Deep-learning-based automatic monitoring of pigs’ physico-temporal
activities at different greenhouse gas concentrations,” Animals, vol. 11, no. 11, Oct. 2021, doi: 10.3390/ani11113089.
15. Int J Elec & Comp Eng ISSN: 2088-8708
Robust individual pig tracking (Aggaluck Jaoukaew)
293
[42] M. Kim, Y. Choi, J. Lee, S. Sa, and H. Cho, “A deep learning-based approach for feeding behavior recognition of weanling pigs,”
Journal of Animal Science and Technology, vol. 63, no. 6, pp. 1453–1463, Nov. 2021, doi: 10.5187/jast.2021.e127.
[43] S. Tu et al., “Automated behavior recognition and tracking of group-housed pigs with an improved DeepSORT method,”
Agriculture, vol. 12, no. 11, Nov. 2022, doi: 10.3390/agriculture12111907.
[44] W. Liu et al., “SSD: single shot multibox detector,” in Computer Vision ECCV 2016, Springer International Publishing, 2016, pp.
21–37.
[45] N. Chengcheng, Z. Huajun, S. Yan, and T. Jinhui, “Inception single shot multibox detector for object detection,” in 2017 IEEE
International Conference on Multimedia and Expo Workshops (ICMEW), Jul. 2017, pp. 549–554, doi:
10.1109/ICMEW.2017.8026312.
[46] Y. Wang, C. Wang, and H. Zhang, “Combining a single shot multibox detector with transfer learning for ship detection using
sentinel-1 SAR images,” Remote Sensing Letters, vol. 9, no. 8, pp. 780–788, Aug. 2018, doi: 10.1080/2150704X.2018.1475770.
[47] Y. Zheng and G. Wu, “Single shot multibox detector for urban plantation single tree detection and location with high-resolution
remote sensing imagery,” Frontiers in Environmental Science, vol. 9, Nov. 2021, doi: 10.3389/fenvs.2021.755587.
[48] T.-Y. Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in 2017
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul. 2017, pp. 936–944, doi: 10.1109/CVPR.2017.106.
[49] T. W. Cenggoro, A. H. Aslamiah, and A. Yunanto, “Feature pyramid networks for crowd counting,” Procedia Computer Science,
vol. 157, pp. 175–182, 2019, doi: 10.1016/j.procs.2019.08.155.
[50] H. Wang and T. Wang, “Multi-scale residual aggregation feature pyramid network for object detection,” Electronics, vol. 12, no.
1, Dec. 2022, doi: 10.3390/electronics12010093.
[51] K. Min, G.-H. Lee, and S.-W. Lee, “Attentional feature pyramid network for small object detection,” Neural Networks, vol. 155,
pp. 439–450, Nov. 2022, doi: 10.1016/j.neunet.2022.08.029.
[52] A. Jaoukaew, W. Suwansantisuk, and P. Kumhom, “Test datasets for individual pig tracking.” 2023, Accessed: May 08, 2023.
[Online]. Available: https://github.com/aggaluck/GT_and_VDOs_Pigs.
[53] Z.-M. Qian, X. E. Cheng, and Y. Q. Chen, “Automatically detect and track multiple fish swimming in shallow water with frequent
occlusion,” Plos One, vol. 9, no. 9, Sep. 2014, doi: 10.1371/journal.pone.0106506.
[54] H. T. Sadeeq and A. M. Abdulazeez, “Giant trevally optimizer (GTO): A novel metaheuristic algorithm for global optimization
and challenging engineering problems,” IEEE Access, vol. 10, pp. 121615–121640, 2022, doi: 10.1109/ACCESS.2022.3223388.
BIOGRAPHIES OF AUTHORS
Aggaluck Jaoukaew received a B.Sc. degree in physics from King Mongkut’s
University of Technology Thonburi (KMUTT), Thailand (2005); and an M.Eng. degree in
electrical and information engineering from KMUTT, Thailand (2008). He is currently pursuing
a doctoral degree in electrical and information engineering technology at the Department of
Electronic and Telecommunication Engineering, KMUTT, Thailand. His main research interests
include image processing, object detection, and behavior recognition. His general interests
include machine learning, the Internet of things, and their applications in computer vision. He
can be contacted at aggaluck.hin@mail.kmutt.ac.th.
Watcharapan Suwansantisuk received B.S. degrees in electrical and computer
engineering and in computer science from Carnegie Mellon University, Pennsylvania, in 2002, and
M.S. and Ph.D. degrees in electrical engineering from the Massachusetts Institute of Technology
in 2004 and 2012, respectively. He is currently an assistant professor at King Mongkut’s
University of Technology Thonburi (KMUTT), Thailand. Before joining KMUTT, he spent
summers at the University of Bologna, Italy, as a visiting research scholar, and at the Alcatel-
Lucent Bells Laboratory, NJ, as a research intern. His main research interests include wireless
communications, synchronization, and statistical signal processing. Dr. Suwansantisuk serves on
the technical program committees for various international conferences and served as the
symposium co-chair for the IEEE Global Communications Conference in 2015. He received the
Leonard G. Abraham Prize in the field of communications systems from the IEEE
Communications Society in 2011, jointly with Prof. M. Chiani and Prof. M. Win, and the
Best Paper Award from the IEEE RIVF International Conference on Computing and
Communication Technologies in 2016, jointly with N. Chedoloh. He can be contacted at
watcharapan.suw@kmutt.ac.th.
Pinit Kumhom received a B.Eng. degree in electrical engineering from King
Mongkut’s Institute of Technology Thonburi, Thailand, in 1988, and a Ph.D. degree in
electrical and computer engineering from Drexel University, Pennsylvania, in 2000. He is
currently an assistant professor with the King Mongkut’s University of Technology Thonburi.
His research interests include the Internet of things and its applications, digital system
design and implementation, and signal and image processing. He can be contacted at
pinit.kumhom@mail.kmutt.ac.th.