In India, traffic control management is a difficult task due to an increment in the number of vehicles for the same infrastructure and systems. In the smart-city project, the Adaptive Traffic Light Control System (ATLCS) is one of the major research concerns for an Intelligent Transportation System (ITS) development to reduce traffic congestion and accidents, create a healthy environment, etc. Here, we have proposed a Vehicular Density Value (VDV) based adaptive traffic light control system method for 4-way intersection points using a selection of rotation, area of interest, and Statistical Block Matching Approach (SBMA). Graphical User Interface (GUI) and Hardware-based results are shown in the result section. We have compared, the normal traffic light control system with the proposed adaptive traffic light control system in the results section. The same results are verified using a hardware (raspberry-pi) device with different sizes, colors, and shapes of vehicles using the same method.
Real-time parking slot availability for Bhavnagar, using statistical block ma...JANAK TRIVEDI
Purpose-The purpose of this paper is to find a real-time parking location for a four-wheeler. Design/methodology/approach-Real-time parking availability using specific infrastructure requires a high cost of installation and maintenance cost, which is not affordable to all urban cities. The authors present statistical block matching algorithm (SBMA) for real-time parking management in small-town cities such as Bhavnagar using an in-built surveillance CCTV system, which is not installed for parking application. In particular, data from a camera situated in a mall was used to detect the parking status of some specific parking places using a region of interest (ROI). The method proposed computes the mean value of the pixels inside the ROI using blocks of different sizes (8 Â 10 and 20 Â 35), and the values were compared among different frames. When the difference between frames is more significant than a threshold, the process generates "no parking space for that place." Otherwise, the method yields "parking place available." Then, this information is used to print a bounding box on the parking places with the color green/red to show the availability of the parking place. Findings-The real-time feedback loop (car parking positions) helps the presented model and dynamically refines the parking strategy and parking position to the users. A whole-day experiment/validation is shown in this paper, where the evaluation of the method is performed using pattern recognition metrics for classification: precision, recall and F1 score. Originality/value-The authors found real-time parking availability for Himalaya Mall situated in Bhavnagar, Gujarat, for 18th June 2018 video using the SBMA method with accountable computational time for finding parking slots. The limitations of the presented method with future implementation are discussed at the end of this paper.
: This paper is aimed at designing a density based dynamic traffic signal system where the timing
of signal will change automatically on sensing the traffic density at any junction using the IoT technology. Traffic
congestion is a severe problem in most cities across the world and therefore it is time to shift more manual mode
or fixed timer mode to an automated system with decision making capabilities. To optimize this problem, we have
made a framework for an intelligent traffic control system. Sometimes higher traffic density at one side of the
junction demands longer green time as compared to standard allotted time. We therefore propose here a
mechanism in which the time period of green light and red light is assigned on the basis of the density of the
traffic present at the time. This is achieved by using LIDAR sensors.
CANNY EDGE DETECTION BASED REAL-TIME INTELLIGENT PARKING MANAGEMENT SYSTEMJANAK TRIVEDI
Real-time traffic monitoring and parking are very important aspects
for a better social and economic system. Python-based Intelligent Parking
Management System (IPMS) module using a USB camera and a canny edge
detection method was developed. The current situation of real-time parking slot
was simultaneously checked, both online and via a mobile application, with a
message of Parking “Available” or “Not available” for 10 parking slots. In
addition, at the time entering in parking module, gate open and at the time of exit
parking module, the gate closes automatically using servomotor and sensors.
Results are displayed in figures with the proposed method flow chart
OpenCVand Matlab based Car Parking System Module for Smart City using Circle ...JANAK TRIVEDI
finding parking availability for a specific time period is
a very tedious job in urban areas. The Indian government now
focusing on t he smart city project, already they published city
name for a n upcoming smart city project. In smart city
application , intelligent transportation system (ITS) plays an
important role- in that finding parking place, specifically for the
car owner to avoid time computation, as well as congestion in
traffic is going to be very important. In this article, we propose
an intelligent car parking system for the smart city using Circle
Hough Transform (CHT).
VEHICLE CLASSIFICATION USING THE CONVOLUTION NEURAL NETWORK APPROACHJANAK TRIVEDI
We present vehicle detection classification using the Convolution
Neural Network (CNN) of the deep learning approach. The automatic vehicle
classification for traffic surveillance video systems is challenging for the Intelligent
Transportation System (ITS) to build a smart city. In this article, three different
vehicles: bike, car and truck classification are considered for around 3,000 bikes,
6,000 cars, and 2,000 images of trucks. CNN can automatically absorb and extract
different vehicle dataset’s different features without a manual selection of features.
The accuracy of CNN is measured in terms of the confidence values of the detected
object. The highest confidence value is about 0.99 in the case of the bike category
vehicle classification. The automatic vehicle classification supports building an
electronic toll collection system and identifying emergency vehicles in the traffic
Classification and Detection of Vehicles using Deep Learningijtsrd
The vehicle classification and detecting its license plate are important tasks in intelligent security and transportation systems. The traditional methods of vehicle classification and detection are highly complex which provides coarse grained results due to suffering from limited viewpoints. Because of the latest achievements of Deep Learning, it was successfully applied to image classification and detection of objects. This paper presents a method based on a convolutional neural network, which consists of two steps vehicle classification and vehicle license plate recognition. Several typical neural network modules have been applied in training and testing the vehicle Classification and detection of license plate model, such as CNN convolutional neural networks , TensorFlow, Tesseract OCR. The proposed method can identify the vehicle type, number plate and other information accurately. This model provides security and log details regarding vehicles by using AI Surveillance. It guides the surveillance operators and assists human resources. With the help of the original training dataset and enriched testing dataset, the algorithm can obtain results with an average accuracy of about 97.32 in the classification and detection of vehicles. By increasing the amount of the data, the mean error and misclassification rate gradually decreases. So, this algorithm which is based on Deep Learning has good superiority and adaptability. When compared to the leading methods in the challenging Image datasets, our deep learning approach obtains highly competitive results. Finally, this paper proposes modern methods for the improvement of the algorithm and prospects the development direction of deep learning in the field of machine learning and artificial intelligence. Madde Pavan Kumar | Dr. K. Manivel | N. Jayanthi "Classification & Detection of Vehicles using Deep Learning" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-3 , April 2020, URL: https://www.ijtsrd.com/papers/ijtsrd30353.pdf Paper Url :https://www.ijtsrd.com/engineering/software-engineering/30353/classification-and-detection-of-vehicles-using-deep-learning/madde-pavan-kumar
Vision-based real-time vehicle detection and vehicle speed measurement using ...JANAK TRIVEDI
In recent trends, digital information to the industrial integration for the intelligent transportation system (ITS)
field is gaining importance for the researcher, academia, and industrial persons. Visual information helps to
manage traffic systems in the industrial forum to build smart cities in developed countries. This paper presents
vision-based real-time vehicle detection and Vehicle Speed Measurement (VSM) using morphology operation and
binary logical process for an unplanned traffic scenario using image processing techniques. Vehicle detection and
VSM help to reduce the number of accidents and improve road network efficiency. The bounding box size for
vehicle detection is flexible according to vehicles’ sizes on the road. We test this system with different colors and
dimensions for a selected Region of Interest (ROI). The ROI sets using the two-line approach. Here, we compare
the proposed system with the inter-frame difference method and the blob analysis method with recall, precision,
and F1 performance parameters.
Real-time parking slot availability for Bhavnagar, using statistical block ma...JANAK TRIVEDI
Purpose-The purpose of this paper is to find a real-time parking location for a four-wheeler. Design/methodology/approach-Real-time parking availability using specific infrastructure requires a high cost of installation and maintenance cost, which is not affordable to all urban cities. The authors present statistical block matching algorithm (SBMA) for real-time parking management in small-town cities such as Bhavnagar using an in-built surveillance CCTV system, which is not installed for parking application. In particular, data from a camera situated in a mall was used to detect the parking status of some specific parking places using a region of interest (ROI). The method proposed computes the mean value of the pixels inside the ROI using blocks of different sizes (8 Â 10 and 20 Â 35), and the values were compared among different frames. When the difference between frames is more significant than a threshold, the process generates "no parking space for that place." Otherwise, the method yields "parking place available." Then, this information is used to print a bounding box on the parking places with the color green/red to show the availability of the parking place. Findings-The real-time feedback loop (car parking positions) helps the presented model and dynamically refines the parking strategy and parking position to the users. A whole-day experiment/validation is shown in this paper, where the evaluation of the method is performed using pattern recognition metrics for classification: precision, recall and F1 score. Originality/value-The authors found real-time parking availability for Himalaya Mall situated in Bhavnagar, Gujarat, for 18th June 2018 video using the SBMA method with accountable computational time for finding parking slots. The limitations of the presented method with future implementation are discussed at the end of this paper.
: This paper is aimed at designing a density based dynamic traffic signal system where the timing
of signal will change automatically on sensing the traffic density at any junction using the IoT technology. Traffic
congestion is a severe problem in most cities across the world and therefore it is time to shift more manual mode
or fixed timer mode to an automated system with decision making capabilities. To optimize this problem, we have
made a framework for an intelligent traffic control system. Sometimes higher traffic density at one side of the
junction demands longer green time as compared to standard allotted time. We therefore propose here a
mechanism in which the time period of green light and red light is assigned on the basis of the density of the
traffic present at the time. This is achieved by using LIDAR sensors.
CANNY EDGE DETECTION BASED REAL-TIME INTELLIGENT PARKING MANAGEMENT SYSTEMJANAK TRIVEDI
Real-time traffic monitoring and parking are very important aspects
for a better social and economic system. Python-based Intelligent Parking
Management System (IPMS) module using a USB camera and a canny edge
detection method was developed. The current situation of real-time parking slot
was simultaneously checked, both online and via a mobile application, with a
message of Parking “Available” or “Not available” for 10 parking slots. In
addition, at the time entering in parking module, gate open and at the time of exit
parking module, the gate closes automatically using servomotor and sensors.
Results are displayed in figures with the proposed method flow chart
OpenCVand Matlab based Car Parking System Module for Smart City using Circle ...JANAK TRIVEDI
finding parking availability for a specific time period is
a very tedious job in urban areas. The Indian government now
focusing on t he smart city project, already they published city
name for a n upcoming smart city project. In smart city
application , intelligent transportation system (ITS) plays an
important role- in that finding parking place, specifically for the
car owner to avoid time computation, as well as congestion in
traffic is going to be very important. In this article, we propose
an intelligent car parking system for the smart city using Circle
Hough Transform (CHT).
VEHICLE CLASSIFICATION USING THE CONVOLUTION NEURAL NETWORK APPROACHJANAK TRIVEDI
We present vehicle detection classification using the Convolution
Neural Network (CNN) of the deep learning approach. The automatic vehicle
classification for traffic surveillance video systems is challenging for the Intelligent
Transportation System (ITS) to build a smart city. In this article, three different
vehicles: bike, car and truck classification are considered for around 3,000 bikes,
6,000 cars, and 2,000 images of trucks. CNN can automatically absorb and extract
different vehicle dataset’s different features without a manual selection of features.
The accuracy of CNN is measured in terms of the confidence values of the detected
object. The highest confidence value is about 0.99 in the case of the bike category
vehicle classification. The automatic vehicle classification supports building an
electronic toll collection system and identifying emergency vehicles in the traffic
Classification and Detection of Vehicles using Deep Learningijtsrd
The vehicle classification and detecting its license plate are important tasks in intelligent security and transportation systems. The traditional methods of vehicle classification and detection are highly complex which provides coarse grained results due to suffering from limited viewpoints. Because of the latest achievements of Deep Learning, it was successfully applied to image classification and detection of objects. This paper presents a method based on a convolutional neural network, which consists of two steps vehicle classification and vehicle license plate recognition. Several typical neural network modules have been applied in training and testing the vehicle Classification and detection of license plate model, such as CNN convolutional neural networks , TensorFlow, Tesseract OCR. The proposed method can identify the vehicle type, number plate and other information accurately. This model provides security and log details regarding vehicles by using AI Surveillance. It guides the surveillance operators and assists human resources. With the help of the original training dataset and enriched testing dataset, the algorithm can obtain results with an average accuracy of about 97.32 in the classification and detection of vehicles. By increasing the amount of the data, the mean error and misclassification rate gradually decreases. So, this algorithm which is based on Deep Learning has good superiority and adaptability. When compared to the leading methods in the challenging Image datasets, our deep learning approach obtains highly competitive results. Finally, this paper proposes modern methods for the improvement of the algorithm and prospects the development direction of deep learning in the field of machine learning and artificial intelligence. Madde Pavan Kumar | Dr. K. Manivel | N. Jayanthi "Classification & Detection of Vehicles using Deep Learning" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-3 , April 2020, URL: https://www.ijtsrd.com/papers/ijtsrd30353.pdf Paper Url :https://www.ijtsrd.com/engineering/software-engineering/30353/classification-and-detection-of-vehicles-using-deep-learning/madde-pavan-kumar
Vision-based real-time vehicle detection and vehicle speed measurement using ...JANAK TRIVEDI
In recent trends, digital information to the industrial integration for the intelligent transportation system (ITS)
field is gaining importance for the researcher, academia, and industrial persons. Visual information helps to
manage traffic systems in the industrial forum to build smart cities in developed countries. This paper presents
vision-based real-time vehicle detection and Vehicle Speed Measurement (VSM) using morphology operation and
binary logical process for an unplanned traffic scenario using image processing techniques. Vehicle detection and
VSM help to reduce the number of accidents and improve road network efficiency. The bounding box size for
vehicle detection is flexible according to vehicles’ sizes on the road. We test this system with different colors and
dimensions for a selected Region of Interest (ROI). The ROI sets using the two-line approach. Here, we compare
the proposed system with the inter-frame difference method and the blob analysis method with recall, precision,
and F1 performance parameters.
Review Paper on Intelligent Traffic Control system using Computer Vision for ...JANAK TRIVEDI
In today scenario city will try to modify in the form of smart city with better facilities in terms of education, social-economic life,
better transportation availability, noise free – Eco-friendly environment availability, and ICT- Information and communication technology
enabler for development in the city. In this paper, we are reviewing different work already done or draft by some research in the field of traffic
control system – for better monitoring, tracking and managing using a computer vision system. Nowadays, most of the city installed with
C.C.T.V. – camera for monitoring the traffic related activity.
The realistic mobility evaluation of vehicular ad hoc network for indian auto...ijasuc
In recent years, continuous progress in wireless communication has opened a new research field in
computer networks. Now a day’s wireless ad-hoc networking is an emerging research technology that
needs attention of the industry people and the academicians. A vehicular ad-hoc network uses vehicles as
mobile nodes to create mobility in a network.
It’s a challenge to generate realistic mobility for Indian networks as no TIGER or Shapefile map is
available for Indian Automotive Networks.
This paper simulates the realistic mobility of the Vehicular Ad-hoc Networks (VANETs). The key feature of
this work is the realistic mobility generation for the Indian Automotive Intelligent Transport System (ITS)
and also to analyze the throughput, packet delivery fraction (PDF) and packet loss for realistic scenario.
The experimental analysis helps in providing effective communication for safety to the driver and
passengers.
Vehicle detection by using rear parts and tracking systemeSAT Journals
Abstract Vision of Indian government; of making 100 smart cities, attracts our attention to intelligent transport system. Traffic flow analysis is a part of intelligent transport system. It mainly contains three parts: vehicle detection, classification and vehicle tracking par t. Recently, there are different detection and tracking methods like computer vision based, magnetic frequency wave based etc. With the rapid development of computer vision techniques, visual detection has become increasingly popular in the transportation field. In urban traffic video monitoring systems, traffic congestion is a common scene that causes vehicle occlusion and is a challenge for current vehicle detection methods.In practical traffic scenarios, occlusion between vehicles often occurs; therefore, it is unreasonable to treat the vehicle as a whole. To overcome this problem we can use part based detection model. In our system the vehicle is treated as an object composed of multiple salient parts, including the license plate and rear lamps. These parts are localized using their distinctive color, texture, and region feature. Furthermore, the detected parts are treated as graph nodes to construct a probabilistic graph using a Markov random field model. After that, the marginal posterior of each part is inferred using loopy belief propagation to get final vehicle detection. Finally, the vehicles’ trajectories are estimated using a Kalman filter and a tracking-based detection technique is realized. This method we can use in daytime as well as night time and in any bad weather condition. Keywords vehicle detection, kalman filter, Markov model, tracking, rear lamps
Vehicle accidents are by all accounts appalling and frightening occasions occurring which cause various deaths. As the number of accidents per year is increasing tremendously and so the lives affected by accidents. There are traditional ways to help the needy or the victim that is informing the right authority but needs assistance or help from others, but this tends to take ample of time and due to it could cost lives. So there is a need to develop an accident detection system that would detect and alert the proper authorities about the accident. The sudden assistance to the alert would in return lead to saving as many lives as possible. Many researchers have analyzed this technique using Convolutional neural network, HDNN, RCNN, etc. This paper will give us an overview of various techniques or methods that are used to detect accidents.
Statistics indicate that most road accidents occur due to a lack of time to react to instant traffic. This problem can be addressed with self-driving vehicles with the application of automated systems to detect such traffic events. The Autonomous Vehicle Navigation System (ATS) has been a standard in the Intelligent Transport System (ITS) and many Driver Assistance Systems (DAS) have been adopted to support these Advanced Autonomous Vehicles (IAVs). To develop these recognition systems for automated self-driving cars, it's important to monitor and operate in real-time traffic events. It requires the correct detection and response of traffic event an automated vehicle. In this paper proposed to develop such a system by applying image recognition to detect and respond to a road blocker by means of real-time distance measurement. To study the performance by measuring accuracy and precision of road blocker detection system and distance calculation, various experiments were conducted by using Shalom frame dataset and detection accuracy, precision of 99%, 100%, while distance calculation 97%, 99% has been achieved by this approach.
Autonomous Traffic Signal Control using Decision Tree IJECEIAES
The objective of this paper is to introduce an effective and efficient way of traffic signal light control to optimize the traffic signal duration across each lanes and thereby, to minimize or completely eliminate traffic congestion. This paper introduces a new approach to resolve the traffic congestion problem at junctions by making use of decision trees. The vehicle count in the real time traffic video is determined by Image Processing technique. This information is fed to the decision tree based on which the decision is made regarding the status of traffic signal lights of each lane at the junction at any given instant of time.
"Detecting road lane is one of the key processes in vision based driving assistance system and autonomous vehicle system. The main purpose of the lane detection process is to estimate car position relative to the lane so that it can provide a warning to the driver if the car starts departing the lane. This process is useful not only to enhance safe driving but also in self driving car system. A novel approach to lane detection method using image processing techniques is presented in this research. The method minimizes the complexity of computation by the use of prior knowledge of color, intensity and the shape of the lane marks. By using prior knowledge, the detection process requires only two different analyses which are pixel intensity analysis and color component analysis. The method starts with searching a strong pair of edges along the horizontal line of road image. Once the strong edge is detected the process continues with color analysis on pixels that lie between the edges to check whether the pixels belong to a lane or not. The process is repeated for different positions of horizontal lines covering the road image. The method was successfully tested on selected 20 road images collected from internet. Ery M. Rizaldy | J. M. Nursherida | Abdul Rahim Sadiq Batcha ""Reduced Dimension Lane Detection Method"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Special Issue | International Conference on Advanced Engineering and Information Technology , November 2018, URL: https://www.ijtsrd.com/papers/ijtsrd19136.pdf
Paper URL: https://www.ijtsrd.com/engineering/civil-engineering/19136/reduced-dimension-lane-detection-method/ery-m-rizaldy"
Artificial intelligence in transportation systemPoojaBele1
A presentation to show the use of artificial intelligence in transportation system.
Artificial Intelligence makes the transportation system more easier.
This presentation contains points to be studies in this field.
Integrated Intelligent Transportation Systems (ITS)Babagana Sheriff
An Implementation of Integrated ITS Solution supporting Mobility as a Service within West Midlands Region, UK in Collaboration of Integrated Transport Authority.
Public transport service is one of the most preferred
modes of transportation in today’s smart cities. People prefer
public transport mainly for the cost benefit reasons. The
problems faced by the people while using the public transport
can be overcome by the technology such as Internet of Things
(IOT). In this paper, we present how this technology can be
applied to eliminate the problems faced by the passengers of the
public bus transport service. The Internet of Things technology is
used to provide the passengers waiting at the bus stop with real
time information of the arriving buses. Information such as
arrival time, crowd density and traffic information of the
arriving buses are predetermined and provided to the passengers
waiting at the bus stop. The display boards fitted at the bus stops
provide the real time bus navigation information to the waiting
passengers. This Smart Bus Navigation system enables the
passengers to make smart decisions regarding their bus journey.
This system reduces the anxiety and the waiting time of the
passenger’s at the bus stop. The smart bus navigation system
creates a positive impact and increases the number of people who
prefer to use the public mode of transportation.
Vehicle Counting Module Design in Small Scale for Traffic Management in Smart...JANAK TRIVEDI
Currently, smart city project is running in INDIA for
urban development. Under this project, intelligent transportation system (ITS) is the very significant step towards achieving the goal of reducing traffic congestion as well as different traffic monitoring applications, like – parking management, emergency vehicle detection, car speed detection, accidents detection, car
counting etc. To achieve intelligent transportation system’s goal
for traffic monitoring, Image and video processing becomes a
significant tool. In this article focus on vehicle counting, or say
car counting for available online video (YouTube) using -
Frame difference, Edge detection, Euclidean distance
methods, Morphology, adaptive threshold and effective
prediction of center position with addition of calculation of
change in positions, delta positions and Gaussian blur. To
differentiate car as an object with another object, we consider
here particular size for car objects or say four-wheeler
objects, which are different then pedestrians available on the
road, as well as different static objects –like a tree, posters
available on road etc. Here simulation results check for
Ahmedabad, Chennai, Bangalore, Mumbai traffic related
video available with different resolution on YouTube. Also
with night traffic conditions. For, Ahmedabad Traffic
video, simulation results validate using recall, precision, and
F1 parameter.
A multi-objective evolutionary scheme for control points deployment in intell...IJECEIAES
One of the problems that hinder emergency in developing countries is the problem of monitoring a number of activities on inter-urban roadway networks. In the literature, the use of control points is proposed in the context of these countries in order to ensure efficient monitoring, by ensuring a good coverage while minimizing the installation costs as well as the number of accidents across these road networks. In this work, we propose an optimal deployment of these control points from several optimization methods based on some evolutionary multi-objective algorithms: the Non dominated sorting genetic algorithm-II (NSGA-II); the multi-objective particle swarm optimization (MOPSO); the strength pareto evolutionary algorithm-II (SPEA-II); and the pareto envelope based selection algorithm-II (PESA-II). We performed the tests and compared these deployments using pareto front and performance indicators like the spread and hypervolume and the inverted generational distance (IGD). The results obtained show that the NSGA-II method is the most adequate in the deployment of these control points.
Review Paper on Intelligent Traffic Control system using Computer Vision for ...JANAK TRIVEDI
In today scenario city will try to modify in the form of smart city with better facilities in terms of education, social-economic life,
better transportation availability, noise free – Eco-friendly environment availability, and ICT- Information and communication technology
enabler for development in the city. In this paper, we are reviewing different work already done or draft by some research in the field of traffic
control system – for better monitoring, tracking and managing using a computer vision system. Nowadays, most of the city installed with
C.C.T.V. – camera for monitoring the traffic related activity.
The realistic mobility evaluation of vehicular ad hoc network for indian auto...ijasuc
In recent years, continuous progress in wireless communication has opened a new research field in
computer networks. Now a day’s wireless ad-hoc networking is an emerging research technology that
needs attention of the industry people and the academicians. A vehicular ad-hoc network uses vehicles as
mobile nodes to create mobility in a network.
It’s a challenge to generate realistic mobility for Indian networks as no TIGER or Shapefile map is
available for Indian Automotive Networks.
This paper simulates the realistic mobility of the Vehicular Ad-hoc Networks (VANETs). The key feature of
this work is the realistic mobility generation for the Indian Automotive Intelligent Transport System (ITS)
and also to analyze the throughput, packet delivery fraction (PDF) and packet loss for realistic scenario.
The experimental analysis helps in providing effective communication for safety to the driver and
passengers.
Vehicle detection by using rear parts and tracking systemeSAT Journals
Abstract Vision of Indian government; of making 100 smart cities, attracts our attention to intelligent transport system. Traffic flow analysis is a part of intelligent transport system. It mainly contains three parts: vehicle detection, classification and vehicle tracking par t. Recently, there are different detection and tracking methods like computer vision based, magnetic frequency wave based etc. With the rapid development of computer vision techniques, visual detection has become increasingly popular in the transportation field. In urban traffic video monitoring systems, traffic congestion is a common scene that causes vehicle occlusion and is a challenge for current vehicle detection methods.In practical traffic scenarios, occlusion between vehicles often occurs; therefore, it is unreasonable to treat the vehicle as a whole. To overcome this problem we can use part based detection model. In our system the vehicle is treated as an object composed of multiple salient parts, including the license plate and rear lamps. These parts are localized using their distinctive color, texture, and region feature. Furthermore, the detected parts are treated as graph nodes to construct a probabilistic graph using a Markov random field model. After that, the marginal posterior of each part is inferred using loopy belief propagation to get final vehicle detection. Finally, the vehicles’ trajectories are estimated using a Kalman filter and a tracking-based detection technique is realized. This method we can use in daytime as well as night time and in any bad weather condition. Keywords vehicle detection, kalman filter, Markov model, tracking, rear lamps
Vehicle accidents are by all accounts appalling and frightening occasions occurring which cause various deaths. As the number of accidents per year is increasing tremendously and so the lives affected by accidents. There are traditional ways to help the needy or the victim that is informing the right authority but needs assistance or help from others, but this tends to take ample of time and due to it could cost lives. So there is a need to develop an accident detection system that would detect and alert the proper authorities about the accident. The sudden assistance to the alert would in return lead to saving as many lives as possible. Many researchers have analyzed this technique using Convolutional neural network, HDNN, RCNN, etc. This paper will give us an overview of various techniques or methods that are used to detect accidents.
Statistics indicate that most road accidents occur due to a lack of time to react to instant traffic. This problem can be addressed with self-driving vehicles with the application of automated systems to detect such traffic events. The Autonomous Vehicle Navigation System (ATS) has been a standard in the Intelligent Transport System (ITS) and many Driver Assistance Systems (DAS) have been adopted to support these Advanced Autonomous Vehicles (IAVs). To develop these recognition systems for automated self-driving cars, it's important to monitor and operate in real-time traffic events. It requires the correct detection and response of traffic event an automated vehicle. In this paper proposed to develop such a system by applying image recognition to detect and respond to a road blocker by means of real-time distance measurement. To study the performance by measuring accuracy and precision of road blocker detection system and distance calculation, various experiments were conducted by using Shalom frame dataset and detection accuracy, precision of 99%, 100%, while distance calculation 97%, 99% has been achieved by this approach.
Autonomous Traffic Signal Control using Decision Tree IJECEIAES
The objective of this paper is to introduce an effective and efficient way of traffic signal light control to optimize the traffic signal duration across each lanes and thereby, to minimize or completely eliminate traffic congestion. This paper introduces a new approach to resolve the traffic congestion problem at junctions by making use of decision trees. The vehicle count in the real time traffic video is determined by Image Processing technique. This information is fed to the decision tree based on which the decision is made regarding the status of traffic signal lights of each lane at the junction at any given instant of time.
"Detecting road lane is one of the key processes in vision based driving assistance system and autonomous vehicle system. The main purpose of the lane detection process is to estimate car position relative to the lane so that it can provide a warning to the driver if the car starts departing the lane. This process is useful not only to enhance safe driving but also in self driving car system. A novel approach to lane detection method using image processing techniques is presented in this research. The method minimizes the complexity of computation by the use of prior knowledge of color, intensity and the shape of the lane marks. By using prior knowledge, the detection process requires only two different analyses which are pixel intensity analysis and color component analysis. The method starts with searching a strong pair of edges along the horizontal line of road image. Once the strong edge is detected the process continues with color analysis on pixels that lie between the edges to check whether the pixels belong to a lane or not. The process is repeated for different positions of horizontal lines covering the road image. The method was successfully tested on selected 20 road images collected from internet. Ery M. Rizaldy | J. M. Nursherida | Abdul Rahim Sadiq Batcha ""Reduced Dimension Lane Detection Method"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Special Issue | International Conference on Advanced Engineering and Information Technology , November 2018, URL: https://www.ijtsrd.com/papers/ijtsrd19136.pdf
Paper URL: https://www.ijtsrd.com/engineering/civil-engineering/19136/reduced-dimension-lane-detection-method/ery-m-rizaldy"
Artificial intelligence in transportation systemPoojaBele1
A presentation to show the use of artificial intelligence in transportation system.
Artificial Intelligence makes the transportation system more easier.
This presentation contains points to be studies in this field.
Integrated Intelligent Transportation Systems (ITS)Babagana Sheriff
An Implementation of Integrated ITS Solution supporting Mobility as a Service within West Midlands Region, UK in Collaboration of Integrated Transport Authority.
Public transport service is one of the most preferred
modes of transportation in today’s smart cities. People prefer
public transport mainly for the cost benefit reasons. The
problems faced by the people while using the public transport
can be overcome by the technology such as Internet of Things
(IOT). In this paper, we present how this technology can be
applied to eliminate the problems faced by the passengers of the
public bus transport service. The Internet of Things technology is
used to provide the passengers waiting at the bus stop with real
time information of the arriving buses. Information such as
arrival time, crowd density and traffic information of the
arriving buses are predetermined and provided to the passengers
waiting at the bus stop. The display boards fitted at the bus stops
provide the real time bus navigation information to the waiting
passengers. This Smart Bus Navigation system enables the
passengers to make smart decisions regarding their bus journey.
This system reduces the anxiety and the waiting time of the
passenger’s at the bus stop. The smart bus navigation system
creates a positive impact and increases the number of people who
prefer to use the public mode of transportation.
Vehicle Counting Module Design in Small Scale for Traffic Management in Smart...JANAK TRIVEDI
Currently, smart city project is running in INDIA for
urban development. Under this project, intelligent transportation system (ITS) is the very significant step towards achieving the goal of reducing traffic congestion as well as different traffic monitoring applications, like – parking management, emergency vehicle detection, car speed detection, accidents detection, car
counting etc. To achieve intelligent transportation system’s goal
for traffic monitoring, Image and video processing becomes a
significant tool. In this article focus on vehicle counting, or say
car counting for available online video (YouTube) using -
Frame difference, Edge detection, Euclidean distance
methods, Morphology, adaptive threshold and effective
prediction of center position with addition of calculation of
change in positions, delta positions and Gaussian blur. To
differentiate car as an object with another object, we consider
here particular size for car objects or say four-wheeler
objects, which are different then pedestrians available on the
road, as well as different static objects –like a tree, posters
available on road etc. Here simulation results check for
Ahmedabad, Chennai, Bangalore, Mumbai traffic related
video available with different resolution on YouTube. Also
with night traffic conditions. For, Ahmedabad Traffic
video, simulation results validate using recall, precision, and
F1 parameter.
A multi-objective evolutionary scheme for control points deployment in intell...IJECEIAES
One of the problems that hinder emergency in developing countries is the problem of monitoring a number of activities on inter-urban roadway networks. In the literature, the use of control points is proposed in the context of these countries in order to ensure efficient monitoring, by ensuring a good coverage while minimizing the installation costs as well as the number of accidents across these road networks. In this work, we propose an optimal deployment of these control points from several optimization methods based on some evolutionary multi-objective algorithms: the Non dominated sorting genetic algorithm-II (NSGA-II); the multi-objective particle swarm optimization (MOPSO); the strength pareto evolutionary algorithm-II (SPEA-II); and the pareto envelope based selection algorithm-II (PESA-II). We performed the tests and compared these deployments using pareto front and performance indicators like the spread and hypervolume and the inverted generational distance (IGD). The results obtained show that the NSGA-II method is the most adequate in the deployment of these control points.
Our journal has been unwavering commitment to showcasing cutting-edge research. The journal provides a platform for researchers to disseminate their work on next-generation technologies. In an era where innovation is the driving force behind progress, JST plays a crucial role in shaping the discourse on emerging technologies, thus contributing to their rapid development and implementation.
A Method for Predicting Vehicles Motion Based on Road Scene Reconstruction an...ITIIIndustries
The suggested method helps predicting vehicles movement in order to give the driver more time to react and avoid collisions on roads. The algorithm is dynamically modelling the road scene around the vehicle based on the data from the onboard camera. All moving objects are monitored and represented by the dynamic model on a 2D map. After analyzing every object’s movement, the algorithm predicts its possible behavior.
CREATING DATA OUTPUTS FROM MULTI AGENT TRAFFIC MICRO SIMULATION TO ASSIMILATI...cscpconf
The intensive development of traffic engineering and technologies that are integrated into vehicles, roads and their surroundings, bring opportunities of real time transport mobility modeling. Based on such model it is then possible to establish a predictive layer that is capable of predicting short and long term traffic flow behavior. It is possible to create the real time model of traffic mobility based on generated data. However, data may have different geographical, temporal or other constraints, or failures. It is therefore appropriate to develop tools that artificially create missing data, which can then be assimilated with real data. This paper presents a mechanism describing strategies of generating artificial data using microsimulations. It describes traffic microsimulation based on our solution of multiagent framework over which a system for generating traffic data is built. The system generates data of a structure corresponding to the data acquired in the real world.
Automated signal pre-emption system for emergency vehicles using internet of ...IAESIJAI
Vehicle administration systems are one of the major highlights especially in urban areas. One important critical component that requires attention are signal preemption systems. Every single work on traffic congestion identification either requires prior learning or long time to distinguish and perceive the closeness of congestion. FutureSight performs predictive analysis and control of traffic signals through the application of machine learning to aide ambulances in such a way that, a signal turns green beforehand so as to ensure an obstacle free path to the ambulance from source to destination based on various parameters such as traffic density, congestion length, previous wait times, arrival time thereby eliminating the need for human intervention. The method allows flexible interface to the driver to enter the hospital details to reach the destination with in time. The app then plans out the fastest route from the pickup spot to the selected hospital and sends this route to the system. The system then predict the amount of time that is required by the signal to remain green so as to clear all traffic at that specific junction before the ambulance arrives at that location.
CREATING DATA OUTPUTS FROM MULTI AGENT TRAFFIC MICRO SIMULATION TO ASSIMILATI...csandit
The intensive development of traffic engineering and technologies that are integrated into
vehicles, roads and their surroundings, bring opportunities of real time transport mobility
modeling. Based on such model it is then possible to establish a predictive layer that is capable
of predicting short and long term traffic flow behavior. It is possible to create the real time
model of traffic mobility based on generated data. However, data may have different
geographical, temporal or other constraints, or failures. It is therefore appropriate to develop
tools that artificially create missing data, which can then be assimilated with real data. This
paper presents a mechanism describing strategies of generating artificial data using
microsimulations. It describes traffic microsimulation based on our solution of multiagent
framework over which a system for generating traffic data is built. The system generates data of
a structure corresponding to the data acquired in the real world.
Saudi Arabia stands as a titan in the global energy landscape, renowned for its abundant oil and gas resources. It's the largest exporter of petroleum and holds some of the world's most significant reserves. Let's delve into the top 10 oil and gas projects shaping Saudi Arabia's energy future in 2024.
Forklift Classes Overview by Intella PartsIntella Parts
Discover the different forklift classes and their specific applications. Learn how to choose the right forklift for your needs to ensure safety, efficiency, and compliance in your operations.
For more technical information, visit our website https://intellaparts.com
Democratizing Fuzzing at Scale by Abhishek Aryaabh.arya
Presented at NUS: Fuzzing and Software Security Summer School 2024
This keynote talks about the democratization of fuzzing at scale, highlighting the collaboration between open source communities, academia, and industry to advance the field of fuzzing. It delves into the history of fuzzing, the development of scalable fuzzing platforms, and the empowerment of community-driven research. The talk will further discuss recent advancements leveraging AI/ML and offer insights into the future evolution of the fuzzing landscape.
Automobile Management System Project Report.pdfKamal Acharya
The proposed project is developed to manage the automobile in the automobile dealer company. The main module in this project is login, automobile management, customer management, sales, complaints and reports. The first module is the login. The automobile showroom owner should login to the project for usage. The username and password are verified and if it is correct, next form opens. If the username and password are not correct, it shows the error message.
When a customer search for a automobile, if the automobile is available, they will be taken to a page that shows the details of the automobile including automobile name, automobile ID, quantity, price etc. “Automobile Management System” is useful for maintaining automobiles, customers effectively and hence helps for establishing good relation between customer and automobile organization. It contains various customized modules for effectively maintaining automobiles and stock information accurately and safely.
When the automobile is sold to the customer, stock will be reduced automatically. When a new purchase is made, stock will be increased automatically. While selecting automobiles for sale, the proposed software will automatically check for total number of available stock of that particular item, if the total stock of that particular item is less than 5, software will notify the user to purchase the particular item.
Also when the user tries to sale items which are not in stock, the system will prompt the user that the stock is not enough. Customers of this system can search for a automobile; can purchase a automobile easily by selecting fast. On the other hand the stock of automobiles can be maintained perfectly by the automobile shop manager overcoming the drawbacks of existing system.
COLLEGE BUS MANAGEMENT SYSTEM PROJECT REPORT.pdfKamal Acharya
The College Bus Management system is completely developed by Visual Basic .NET Version. The application is connect with most secured database language MS SQL Server. The application is develop by using best combination of front-end and back-end languages. The application is totally design like flat user interface. This flat user interface is more attractive user interface in 2017. The application is gives more important to the system functionality. The application is to manage the student’s details, driver’s details, bus details, bus route details, bus fees details and more. The application has only one unit for admin. The admin can manage the entire application. The admin can login into the application by using username and password of the admin. The application is develop for big and small colleges. It is more user friendly for non-computer person. Even they can easily learn how to manage the application within hours. The application is more secure by the admin. The system will give an effective output for the VB.Net and SQL Server given as input to the system. The compiled java program given as input to the system, after scanning the program will generate different reports. The application generates the report for users. The admin can view and download the report of the data. The application deliver the excel format reports. Because, excel formatted reports is very easy to understand the income and expense of the college bus. This application is mainly develop for windows operating system users. In 2017, 73% of people enterprises are using windows operating system. So the application will easily install for all the windows operating system users. The application-developed size is very low. The application consumes very low space in disk. Therefore, the user can allocate very minimum local disk space for this application.
Courier management system project report.pdfKamal Acharya
It is now-a-days very important for the people to send or receive articles like imported furniture, electronic items, gifts, business goods and the like. People depend vastly on different transport systems which mostly use the manual way of receiving and delivering the articles. There is no way to track the articles till they are received and there is no way to let the customer know what happened in transit, once he booked some articles. In such a situation, we need a system which completely computerizes the cargo activities including time to time tracking of the articles sent. This need is fulfilled by Courier Management System software which is online software for the cargo management people that enables them to receive the goods from a source and send them to a required destination and track their status from time to time.
Explore the innovative world of trenchless pipe repair with our comprehensive guide, "The Benefits and Techniques of Trenchless Pipe Repair." This document delves into the modern methods of repairing underground pipes without the need for extensive excavation, highlighting the numerous advantages and the latest techniques used in the industry.
Learn about the cost savings, reduced environmental impact, and minimal disruption associated with trenchless technology. Discover detailed explanations of popular techniques such as pipe bursting, cured-in-place pipe (CIPP) lining, and directional drilling. Understand how these methods can be applied to various types of infrastructure, from residential plumbing to large-scale municipal systems.
Ideal for homeowners, contractors, engineers, and anyone interested in modern plumbing solutions, this guide provides valuable insights into why trenchless pipe repair is becoming the preferred choice for pipe rehabilitation. Stay informed about the latest advancements and best practices in the field.
Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...Dr.Costas Sachpazis
Terzaghi's soil bearing capacity theory, developed by Karl Terzaghi, is a fundamental principle in geotechnical engineering used to determine the bearing capacity of shallow foundations. This theory provides a method to calculate the ultimate bearing capacity of soil, which is the maximum load per unit area that the soil can support without undergoing shear failure. The Calculation HTML Code included.
Quality defects in TMT Bars, Possible causes and Potential Solutions.PrashantGoswami42
Maintaining high-quality standards in the production of TMT bars is crucial for ensuring structural integrity in construction. Addressing common defects through careful monitoring, standardized processes, and advanced technology can significantly improve the quality of TMT bars. Continuous training and adherence to quality control measures will also play a pivotal role in minimizing these defects.
Event Management System Vb Net Project Report.pdfKamal Acharya
In present era, the scopes of information technology growing with a very fast .We do not see any are untouched from this industry. The scope of information technology has become wider includes: Business and industry. Household Business, Communication, Education, Entertainment, Science, Medicine, Engineering, Distance Learning, Weather Forecasting. Carrier Searching and so on.
My project named “Event Management System” is software that store and maintained all events coordinated in college. It also helpful to print related reports. My project will help to record the events coordinated by faculties with their Name, Event subject, date & details in an efficient & effective ways.
In my system we have to make a system by which a user can record all events coordinated by a particular faculty. In our proposed system some more featured are added which differs it from the existing system such as security.
A VISION-BASED REAL-TIME ADAPTIVE TRAFFIC LIGHT CONTROL SYSTEM USING VEHICULAR DENSITY VALUE AND STATISTICAL BLOCK MATCHING APPROACH
1. Transport and Telecommunication Vol. 22, no.1, 2021
87
Transport and Telecommunication, 2021, volume 22, no. 1, 87–97
Transport and Telecommunication Institute, Lomonosova 1, Riga, LV-1019, Latvia
DOI 10.2478/ttj-2021-0007
A VISION-BASED REAL-TIME ADAPTIVE TRAFFIC LIGHT
CONTROL SYSTEM USING VEHICULAR DENSITY VALUE
AND STATISTICAL BLOCK MATCHING APPROACH
Janak D. Trivedi1
, Mandalapu Sarada Devi2
, Dhara H. Dave3
1
Government Engineering College Bhavnagar, Electronics & Communication Department,
Gujarat Technological University,
Gujarat, India
Trivedi_janak2611@yahoo.com
In India, traffic control management is a difficult task due to an increment in the number of vehicles for the same
infrastructure and systems. In the smart-city project, the Adaptive Traffic Light Control System (ATLCS) is one of the major
research concerns for an Intelligent Transportation System (ITS) development to reduce traffic congestion and accidents, create a
healthy environment, etc. Here, we have proposed a Vehicular Density Value (VDV) based adaptive traffic light control system
method for 4-way intersection points using a selection of rotation, area of interest, and Statistical Block Matching Approach
(SBMA). Graphical User Interface (GUI) and Hardware-based results are shown in the result section. We have compared, the
normal traffic light control system with the proposed adaptive traffic light control system in the results section. The same results are
verified using a hardware (raspberry-pi) device with different sizes, colors, and shapes of vehicles using the same method.
Keywords: Adaptive Traffic Light Control System (ATLCS), vehicular-density value (VDV), area of interest (AOI), raspberry-pi,
Intelligent Transportation System (ITS), Graphical User Interface (GUI)
1. Introduction
The violation of traffic light control systems can cause an accident. According to the Ministry of
Road Transport and Highways (MORTH), India ranked 1st among the number of road accident deaths
across the 199 countries in the World Road Statistics in 2018. A total of 4,67,044 road accidents have
been reported which is increased by 0.46% compared to the year 2017. ATLCS does not reduce traffic
accident but it’s also avoided traffic collisions/congestions problem, reduce time-delay, etc. ATLCS
requires continuous data or information from respective intersection points to the control unit at
respective urban areas. Information Communication Technology (ICT) is useful for the development of
smart cities and ITS.
In recent years, different image-video processing-based methodology is very useful for the
development of an ITS. An autonomous vehicle requires this must technology for better reliability, safety,
and flexibility. A Global Positioning System (GPS) opens the door for Vehicle to Vehicle (V2V), Vehicle
to Infrastructure (V2I), Vehicle and handheld device (V2D), and Connected Vehicle Signal Control
Strategy (CVSC). In this paper, we have used the image-video processing-based methodology for the
development of ATLCS.
1.1. Motivation
Since the intelligent method of traffic light control system developed as per offline tool,
TRANSYT (Robertson, 1969), Fixed time-plans for traffic junction, need to be enhanced and technology
adaptive. Adaptive Traffic Light Control System is applied for real-time traffic information to minimize
the delay of traffic, minimize the delay of pedestrians, minimize the delay of public transport, maximize
reliability, minimize environmental impact, etc. A fixed time interval-based traffic light control system
cannot accommodate day to day traffic congestion.
One of the limitations of Sensor-based optimizer to adequate with real-time traffic condition also the
same time requires synchronization of individual Inductive Loop Detector (ILD) and requires additional
installation if not installed earlier. In the case of a fixed-time traffic signal, we have to wait for a complete
cycle of rotation with fixed time whether traffic is present or absent., whereas in case Adaptive Traffic Light
Control System traffic time interval can be changed based on a different strategy or a traffic model.
2. Transport and Telecommunication Vol. 22, no.1, 2021
88
Different road-traffic models are discussed by Mfenjou et al. (2018). Maxband (Maximize
Bandwidth) includes a two-way main road, with specifying passage time between the intersection point.
Transyst (Traffic Network Study Tool) works on off-line optimization, which requires a lot of input
parameters at intersection points. Prodyn is an adaptive traffic system for minimizing delay at intersection
points. OPAC (Optimized Policies for Adaptive Control) works on a dynamic algorithm for minimizing
stops at intersection points, the upgraded version of the system is OPAC-1,2,3 and 4. SCOOT (Split
Cycle and Offset Optimization Technique) is an optimized control system that includes the duration of
green light, offset between neighbouring intersections, and light cycles. This system also collects
information about the number of vehicles per time interval. SCATS (Sydney Coordinated Adaptive
Traffic System) is used information from sensors installed on the road for changing real-time traffic light
plans at intersection points. Rhodes (Real-time Hierarchical Optimized Distributed Effective System)
works on the concept of vehicular network. Insync has used image processing techniques for detecting
vehicles and change traffic signals accordingly in real-time as per traffic demand.
1.2. Organisation of the paper
The remaining part of the paper is organized as follows: In Section 2, we have presented the
Traffic Control System (TCS) using a different methodology. This part presents a survey of different
image-video processing techniques, trends, and applications for the ITS. This part also indicates future
scope from each of the respective articles. In section 3, we have presented the proposed method with a
flowchart. In this part statistical block matching (SBMA) approach with pseudocode is explained. Section
4 and section 5 are indicating the GUI-based adaptive traffic control system and the Raspberry-pi
(Hardware) –based adaptive traffic control system and results respectively. As for section 6, we have
discussed the methodology and results with its objective outcomes. Finally, section 7 shows the
conclusion and future scope of the presented work.
2. Traffic Control Management System using a different methodology
An image-video analysis is useful in traffic control management in terms of real-time an automatic
parking management system, adaptive traffic control system, vehicle classification, automatic vehicle
guidance system in a driverless vehicle, detection of static or movable objects, speed measurements,
vehicle counting, incident detection such as an accident or congestion, automatic lane finding, different
sign detection and recognition, and many more could be added in the list.
Kastrinaki et al. (2003) have explained a survey on a different aspect of video-processing
techniques. Automatic Lane Finding (ALF) and Object detection for the stationary and moving camera
are discussed with different approaches. ALF is discussed using (1) lane-region detection (2) feature and
(3) model-driven approaches. Object detection is explained using (1) Thresholding (2) Multigrid
identification of Region of Interest(ROI) (3) Edge-based detection (spatial differentiation) (4) Space
signature (5) Background frame differencing (6) inter-frame differencing (7) Time signature (8) Feature
aggregation and object tracking (9) Optical flow field (10) Motion parallax (11) Stereo vision (12) Inverse
perspective mapping (13) 3D Modelling and forward mapping. In smart traffic management or adaptive
traffic management is required (A) quickly changes and adapt system accordingly environmental changes
and (B) automatic updating data or information from different sources.
Lozano et al. (2009) have presented Total Recognition by Adaptive Classification Experiments
(TRACE) is described in this paper using feature selection/feature extraction with the help of the k-means
clustering algorithm. The future scope from this article is finding real-time proper vehicle classification
and vehicle counting. Video processing is a useful tool for finding vehicle velocity, stopped vehicles,
travel time and queue length, traffic density for measurement of an automatic traffic control system,
license plate detection, incident detection, vehicle size and vehicle shape for vehicle classification &
vehicle counting approaches, lane departure warning (or ALF), vehicle direction and traffic sign detection
and recognition for driverless vehicle approach using Hough Transform in Bubenikova et al. (2012) for
Advance Driver Assistance System (ADAS).
Mu et al. (2015) has explained the traffic light detection and recognition process, firstly from RGB
(Red-Green-Blue) to HSV (Hue-Saturation-Value) conversion then apply the filtering process and finally
for recognition, a histogram of oriented gradients (HOG) features and Support Vector Machine (SVM) is
used. ADAS is required for the detection and recognition of not only circular traffic lights but also traffic
lights in a horizontal and vertical arrangement. Trained Red, Yellow, and Green traffic light and
3. Transport and Telecommunication Vol. 22, no.1, 2021
89
Gaussian-like traffic light colour distribution are assumed. The limitation of the proposed method is that
the method performs well only in daytime and false measurement increase during night time. Future work
is the detection and recognition of more types of traffic lights.
Intelligent Transportation System (ITS) in a smart city or a smart road requires continuous
monitoring of traffic data with good quality of image/video for the betterment of traffic engineering is
explained by Bommes et al. (2016). The author analysed traffic with (1) Automatic Incident Detection
(AID) of a dangerous traffic situation (2) Traffic count: direction detection of vehicles by Automatic
Number/License Plate Recognition (ANPR/ALPR) (3) State recognition: classify traffic like congestion,
slow traffic, and dense traffic. In that process Optical flow method and frame differencing method was
used (4) Traffic management: video detection system for a dangerous object, shortening decision travel
time, parking lot monitoring and management system, vehicle counting using Principal Component
Analysis (PCA) (5) Measuring speed, toll collection, etc. Different application-wise technology matrix is
mapped in terms of vision details as (a) Traffic webcam resolution (b) Traffic surveillance camera
resolution (c) High-detail camera resolution. Future applications categorized as (i) Short-term, in which
automatic recognition and automatic incident detection with the adaptive traffic control system is targeted
(ii) Mid-term, in which Video-based technology for a better environment is focused and (iii) long-term, in
which Communication with automated vehicles is set.
Chandan et al. (2017) has described as Connected Vehicle Signal Control (CVSC) for speed and
location information using Global Positioning System (GPS) enabled vehicles. This method is compared
with an adaptive traffic signal control simulation developed by PTV EPICS. Different traffic situations
were tested in VISSIM 8 microscopic simulation tool. Limitation of Connected Vehicles (CV) during
communication failure, which decreases the penetration rate. Future work is in the direction of real-time
implementing the proposed method for adaptive traffic control management.
Makino et al. (2018) have given detail of Electric Toll Correction (ETC), Vehicle Information
Communication Service (VICS), ETC 2.0 technology development as a part of the Intelligent
Transportation System (ITS) in Japan. The combination of automatic driving system, ETC 2.0 is helpful
for driver information about changing routes, changing lanes, avoid a collision, etc.
Traffic management project in Phnom Penh, the capital city of the Kingdom of Cambodia is
discussed by S. Matsuoka (2018). Mainly two objectives are explained: (1) improve road traffic
conditions with the help of a traffic control system, pavement markings, traffic signs, median dividers (2)
transfer traffic management technology to local counterparts so that the project continues. First, this
project is analysed before the implementation of the project: (i) the total number of registered vehicles (ii)
traffic condition with a variety of vehicles, roads, driving behaviour, shortage of parking spaces (iii)
pavement markings, traffic signs and other facilities. This project method is assessed with the listed
benefits in the city like an increase in average speed and reduction in fuel consumption, emission, stop,
delay, crash, travel time. The adaptive traffic control system with the same traffic volume for 2
intersection points with enabling and disabling during 1-hour time duration is measured and results are
more prominent for enable condition of the adaptive traffic control system. Future challenges are listed as
(a) proper operation and maintenance of the system (b) safety education and campaigning traffic rules
among road users (c) expansion and up-gradation of the system.
Krzysztof et al. (2018) have explained smaller size cells compared to the Negel-Schreckenberg
traffic model using cellular automaton (CA). The model is demonstrated with different driver behaviours:
(1) The carefree driver (2) The driver with little skills (3) The standard driver. In this article, the count-
down timer effect is useful for different driver approaches positively. Future work with more reliability of
work, from a traffic light, mounted at intersection points.
Zhang et al. (2018) have described as a traffic decision using Case-Based Reasoning (CBR) and
was verified by example. Different modules are considered for traffic management easy of operation,
listed as (1) traffic information acquisition module (2) emergency scene information module (3) human-
computer interface module (4) emergency modelling module (5) aid decision-making module and (6)
database module. Generally, the CBR case solving process includes four steps (a) Retrieve -the case (b)
Reuse- case information and knowledge (c) Revise- if the large difference between previous and targeted
case (d) Retain – the new solution. In this paper, case base characteristic attributes are mainly traffic peak,
traffic type, place, whether, area, number of causalities, and number of damaged cars, and many more.
Find similarities of various attributes in terms of (i) local similarity – enumerated, numerical, fuzzy (ii)
overall similarity.
Rabbouch et al. (2018) has proposed an online video processing based automatic traffic control
system model using Motion Intensity Index (MII) with a cumulating vision score frame by frame. After
simple regression (linear regression) and wavelet regression (independent regression) forecast and convert
MII into several vehicles for expected traffic flow counting and monitoring. Mfenjou et al. (2018) have
explained different methodology-technology, application, and trends for developing an Intelligent
4. Transport and Telecommunication Vol. 22, no.1, 2021
90
Transportation System (ITS) in sub-Saharan Africa countries using Information Communication
Technology (ICT). A hybrid system, a combination of four modules is discussed: (1) autonomous
management of control system- to maximize communication coverage and a minimum number of control
points (2) detection and diffusion of disturbance- to reduce congestion (3) dynamic route planning which
is collaborated with disturbance detection (4) monitoring of sections- to reduce accidents in the road.
3. The Proposed method with flow-chart
Figure 1. Flow-chart of the proposed method
Figure 2. Flow-chart of rotation, area of interest, SBMA, VDV
A real-time ATLCS is developed using database management, selection of area of interest,
selection of different image-video related properties for four-way intersection points, and combination of
VDV and SBMA. Figure 1 represents the flowchart of the proposed method and figure 2 represents
cropping, rotation, area of interest, SBMA, and VDV. In a normal traffic light control systems timing
rotation and interval both are fixed irrelevant of any traffic condition, whereas in ATLCS visual
information and vehicle density-based traffic timers are changing continuously.
5. Transport and Telecommunication Vol. 22, no.1, 2021
91
We have implemented our proposed method in software and hardware. GUI-based and Hardwar
(Raspberry-pi)-based results are shown in result sections. SBMA, VDV method, and Pseudocode are
represented in sections 3.1 and 3.2. Real-time video or location are inserted in GUI formation for video-
1,2,3 and 4 respectively. Rotation is one of the important selections for a proper selection of are of
interest as well as for a vehicle density information. A simple 0o
, 90o
- left, 90o
- right, and 180o
rotation
are required as per the selection of visual information. One of the novels approaches in the proposed
method is the selection of a reference frame implemented using VDV. In the case of background
subtraction method normally reference frame is selected, when there is no object in the image, whereas in
the proposed method, liberty of selection for the reference frame. That first frame may contain a large
number of objects, a small number of the object or none of them. We can also select an area of interest at
any instant of time for real-time ATLCS measurements along with intersection points after cropping,
rotation, and VDV is explained in section 3.1 with sets of equations and with pseudocode in section 3.2.
This method works with spatial domain in the field of image-processing techniques.
3.1. SBMA & VDV
min ( , )
ul ll
X Min x x
and max ( , )
ur lr
X Max x x
, (1)
min (y ,y )
ul ll
Y Min
and max (y ,y )
ur lr
Y Max
, (2)
max min 1
dist
X X X
and max min 1
dist
Y Y Y
, (3)
If y y *y
ul ur ul dist ul
x X
else
y y
y y
1
ur ul
ul ul ur
dist
x
X
, (4)
If y y *y
ll lr ll dist ll
x X
else
y y
y y
1
lr ll
ll ll lr
dist
x
X
, (5)
If *x
ul ur ul dist ul
x x y Y
else
1
ur ul
ul ul ur
dist
x x
y x x
Y
, (6)
If *x
ll lr ll dist ll
x x y Y
else
1
lr ll
ll ll lr
dist
x x
y x x
Y
, (7)
4
1
( 1)*90
j
j
, (8)
1
[ ]
n
ref crop
i
A i i
and
1
1
[A ]
N
i
i
mean
N
, (9)
( ( ))
VDV mean mean AOI
, (10)
if R 1
i c c s
f f f
else c c l
f f f
. (11)
All the abbreviations are as mentioned below:
Xmin is minimum value of X-point, Xmax is maximum value of x-point,
Ymin is minimum value of Y-point, Ymax is maximum value of y-point,
xul is upper-left value of x-point, yul is upper-left value of y-point,
xll is lower-left value of x-point, yll is lower-left value of y-point,
xur is upper-right value of x-point, yur is upper-right value of y-point,
xlr is lower-right value of x-point, ylr is lower-right value of y-point
Xdist is distance of x-point from a center location, Ydist is distance of y-point from a center location,
Ri represents ith
road location (here i=1,2,3 or 4), fl represents last-product calculation,
fc represents current-Frame of the selected road, fs represents total number of skipped frames road,
iref represents reference-image intensity value, icrop represents crop-image intensity value.
All the statistics block-matching approach and cropping measurements of the selected roads are
done using a defined set of equations (1) to (7). After reading the video, rotate video with the desired
6. Transport and Telecommunication Vol. 22, no.1, 2021
92
direction using selected theta (θ) if required. Here, θ values are varied as 0o
, 90o
-left, 90o
-right, and 1800
,
which is derived using equation (8). Vehicle Density Value is measured using equation (9) and (10) with
the combination of mean values of selected AOI row and column position. After selection of rotation,
video, crop, area of interest, density values, GUI simulation provides ATLCS with timing and light
control as well as remaining time of current junction and vehicle on-off time, to the next junction, i.e. If
road-A indicates green signal then next 5 seconds is waiting time with yellow signal for the road- A and
the same time with same yellow signal for Road-B provides information, ‘about to start’ this junction. In
a fixed-time interval traffic light control system, the interval is fixed irrespective of vehicle information
on the road, so there is not about-to start information needed. This way the proposed method also controls
air pollution and gives better environmental conditions. In the process of GUI simulation when one road
act as active at the same time another road should be passive. This is done using equation (11).
In this method, VDV is calculated using the mean of the selected AOI. First select, AOI for the
selected roadside in the traffic signal. AOI calculates pixels’ values information using matrix-vector
operation for the selected region. The first time ‘mean’ operation applies to selected region which
calculates mean of row and column pixel value. Then again ‘mean’ operation applies which provides
single value. That single value represents density value information for the selected traffic roadside.
Nowadays, traffic surveillance systems available to monitor traffic in the city. In this article, θ
represents the rotation of the camera situated at four-way intersection points in the city. θ value is varied
as 0o
which represents traffic situation capture with camera position at traffic Road-A (fixed camera
position), θ value is varied as 90o
-left which represents traffic situation capture with camera position at
traffic Road-B (camera rotates in 90o
–left direction), and similar condition for the different choices of θ.
The single-camera situated at four-way intersection points with rotation facility can also monitor traffic
signals at the traffic junction using the rotation θ. The selection of θ is not a necessary step to implement
this method.
3.2. Pseudocode
Time difference = Time out for traffic light
If road==1 to 4, Current threshold = from final image 1 to 4
Otherwise, Current threshold = 0
If road==1 to 4, Minimum threshold = Adaptive Threshold value
Otherwise, Minimum threshold = 0
Traffic Light Condition
Waiting Time (Yellow color) = 5 Second
Allow time (Green Light) = 15 Second
Time difference = Time out for traffic light
If road 1 to 4 selected but video not uploaded,
If, Time difference < Required stop time
Set traffic time, with Stop=Red signal,
Otherwise, Time difference > Required stop time
Start timer count
If road 1 then change road 2
If road 2 then change road 3
If road 3 then change road 4
If road 4 then change road 1
Color change
Current Threshold > Adaptive Threshold value and Time difference < Allow time
Traffic timer stops.
Current Threshold < Adaptive Threshold value or Time difference > Allow time
Traffic timer stops and goes to the next road.
Color Change Function in times box
Number1= Red
Number2= Green
Number3= Yellow
Display Traffic time
Four different roads
Use Number to string operation, display road wise respectively
7. Transport and Telecommunication Vol. 22, no.1, 2021
93
4. Result: GUI-based adaptive traffic control system
Figure 3 represents all roads A, B, C, D are blocked with a red signal. Figures 4 and 5 are shown
with a yellow and a green light signal. For controlling air pollution, a wait signal is operated in two
continuous roadsides. After completion of a green signal in the road-A side, a yellow signal indicates the
reserved time for vehicles, at the same time the same reserved period indicates vehicle start time to Road-B.
In the current scenario vehicles engine are mostly in on condition at the junction points, so this reserved
period is helpful for vehicle engine ON/OFF time.
Figure 3. The starting phase with all red signal
Figure 4. A yellow signal – waiting time 5 seconds
8. Transport and Telecommunication Vol. 22, no.1, 2021
94
Figure 5. A green signal in one direction for 15 seconds
5. Result: Raspberry-pi (Hardware)-based adaptive traffic control system module
Figure 6. (a) Prototype model (b) Model connected using Raspberry-pi (c) Result for adaptive traffic
control system using Raspberry-pi
The same method is uploaded to the raspberry-pi module. A hardware implementation of the
raspberry-pi module is done using Simulink. During uploading the program to hardware first step is
checking board parameter values with the connected environment. Then the next step is to select the build
options, Serial Peripheral Interference (SPI) bus speed, external mode, and ports. With the help of
deploying function, the same algorithm is programmed into raspberry-pi.
Figure 6 (a), (b), and (c) represent the prototype model and results for ATLCS. The proposed
method is also applied in hardware with the use of the raspberry-pi 3B model. This hardware does not
require any additional software installation; we can just plug into any monitoring system. Here, real-time
ATLCS is managed in a prototype model with different vehicle sizes, shapes, colors, and numbers.
9. Transport and Telecommunication Vol. 22, no.1, 2021
95
3 different colors Light Emitting Diode (LED) with green, yellow, and red are used. Green LED for
indication of ‘Drive’ status, yellow for ‘Wait’ status, and red for ‘Stop’. Here, visual information is
obtained using a USB camera. The display device is used for monitoring results. In monitoring screen
waiting time, stop time, and drive time is continuously indicating with real-time changes in toy car
replacement.
Table 1. Video Properties used in GUI simulation, resolution 640 X 360 frame rate in frames/second
Road Total
Frame
Frame
Rate
Rotation Cropping Area of Interest Density
value$
Road-A 9000 30 180 [270,635,10,355] [1,360,10,145] ~5-10
Road-B 8992 29.97 90-Left [150,350,10,450] [80,200,1,430] ~3-7
Road-C 7500 25 0 [320,640,1,355] [1,315,180,350] ~1-2
Road-D 7193 23.98 90-Left [1,360,1,640] [35,185,15,640] ~18-25
$
Density values are selected from the probability of allowable time/vehicles for a particular road-side. It may be varied with
different parameters.
VDV is depended mainly on AOI, vehicle color and size, number of vehicles. In the presented
method, VDV is decided by trial and error method with maximum likelihood possibility for managing
ATLCS. Different values of VDV can affect the number of passing vehicles, light, and timing of the TCS.
The pseudocode represents the use of traffic light condition, timers, adaptive thresholding, color changes,
and display traffic timer function for the proposed ATLCS.
Table 2. Compare the timing diagram for a different traffic control system
Traffic Control System Timing in second, stop time – 40, drive time – 15, wait time – 5.
Road A Road B Road C Road D
Fixed Traffic Light Control
System
15 + 5 40 40 40
40 15 + 5 40 40
40 40 15 + 5 40
40 40 40 15 + 5
Fixed Traffic Light Control
System (Without VDV, With
Remaining time, full traffic)
15 + 5 40 – 5 40 40
40 15 + 5 40 – 5 40
40 40 15 + 5 40 – 5
40 – 5 40 40 15 + 5
Fixed Traffic Light Control
System (With VDV*, With
Remaining time, full traffic)
15 + 5 30 – 5 45 – 5 60 – 5
60 – 5 15 + 5 30 – 5 45 – 5
45 – 5 60 – 5 15 + 5 30 – 5
30 – 5 45 – 5 60 – 5 15 + 5
Adaptive (With VDV*, With
Remaining time, controlled
traffic)
10 + 5 25 – 5 40 – 5 55 – 5
57 – 5 12 + 5 27 – 5 42 – 5
38 – 5 53 – 5 8 + 5 23 – 5
29 – 5 44 – 5 59 – 5 14 + 5
* As per changes in VDV values complete cycle rotation of road A-B-C-D-A also vary, it provides always a higher number of cycle
rotation compares to normal traffic light control system.
6. Discussion
We have proposed a vision based constant ATLCS for a 4-way crossing point, utilizing a
determination of turn, AOI, VDV, and SBMA. Figure (1) and figure (2) shows a flowchart of the
proposed technique. Figure (3) to figure (6) speaks to Graphical User Interface (GUI) based simulation
results for 4-way intersection point (Sub-figures are turned according to single-camera see with a fixed
situation at crossing point). Similar outcomes are additionally checked to utilize equipment (raspberry-pi)
with various sizes, colours, and shapes of vehicles utilizing a similar technique. A prototype module
appears in figure 6(a), figure 6(b) shows associated set-up of equipment and screen, and in figure 6(c)
shows the result for versatile traffic light control framework utilizing equipment (raspberry-pi) gadget
with "Pause" (for 15 second or no vehicle out and about) and "Drive" (for 45 seconds or most extreme
number of vehicles for particular side) message on the screen. S. Srivastava et al. (2016) expresses
ATLTC with a period stream outline for a solitary side, though here the proposed technique for a 4-way
intersection point. In the outcome segment we have compared, the typical traffic light control framework
with the proposed versatile traffic light control framework in Table 2 with the assistance of the span of
time-stamps.
10. Transport and Telecommunication Vol. 22, no.1, 2021
96
The proposed technique is expelled restriction of fixed time traffic light control framework
structured by offline tool TRANSYT (1969). This technique likewise controls traffic at the 4-way
crossing point focuses, which is an improved adaptation of the ATLTC (2016). Table 1 shows various 4-
video properties and Table 2 shows the correlation of the diverse traffic control frameworks with the
planning cycle.
7. Conclusions & Future-scope
We present, vision-based continuous ATLCS. This strategy gives an improvement as far as a more
noteworthy number of complete cycle revolution for road, for example, A-B-C-D-A compared with the
fixed traffic-light control framework. If there is no vehicle or few vehicles present at any single (road-
side-A), opposite side streets (road-side B, C, D) get profited in the wake of discovering relative vehicle
density data. As appeared in table 2, road A, B, C, and D decrease 5, 3, 7, and 1-second cycle revolution
individually compared to fixed time traffic light control system. The proposed strategy limits traffic delay
which helps to reduce traffic congestions, environmental effects. The reserved-time idea is likewise
valuable for the information on vehicle on-off time, it might assist with lessening fuel utilization just as a
superior natural condition. The constraint of this work is, the proposed technique relies upon the vision
framework introduced at convergence focuses that have variable video properties.
In a future work try to installed the proposed method for any junction points to obtain the
outcomes and effect on the same.
References
1. Robertson, D. I. (1969) TRANSYT: A Traffic Network Study Too, RRL Report LR 253, Road
Research Laboratory Crowthorne, Berkshire.
2. Kastrinaki, V., Zervakis, M., Kalaitzakis, K. (2003) A survey of video processing techniques for
traffic applications. Image Vis. Comput., 21(4), pp. 359–381.
3. Lozano, A., Manfredi, G., Nieddu, L. (2009) An algorithm for the recognition of levels of
congestion in road traffic problems. Math. Comput. Simul., 79(6), pp. 1926–1934.
4. Bubeníková, E., Muzikářová, L., Halgaš, J. (2012) Application of image processing in intelligent
transport systems. IFAC Proc. Vol., 11(1), pp. 53–56.
5. Mu, G., Xinyu, Z., Deyi, L., Tianlei, Z., Lifeng, A. (2015) Traffic light detection and recognition for
autonomous vehicles. J. China Univ. Posts Telecommun., 22(1), pp. 50–56.
6. Nemade, B. (2016) Automatic Traffic Surveillance Using Video Tracking. Procedia Comput. Sci.,
79, pp. 402–409.
7. Małecki, K. (2016) The Importance of Automatic Traffic Lights Time Algorithms to Reduce the
Negative Impact of Transport on the Urban Environment. Transp. Res. Procedia, 16(March),
pp. 329–342.
8. Bommes, M., Fazekas, A., Volkenhoff, T., Oeser, M. (2016) Video Based Intelligent Transportation
Systems - State of the Art and Future Development. Transp. Res. Procedia, 14, pp. 4495–4504.
9. Srivastava, S. et al. (2016) Adaptive Traffic Light Timer Control (ATLTC), Adaptive Traffic Light
Timer Control (ATLTC) – NERD.
10. Chandan, K., Seco, A. M., Silva, A. B. (2017) Real-time Traffic Signal Control for Isolated
Intersection, using Car-following Logic under Connected Vehicle Environment. Transp. Res.
Procedia, 25, pp. 1610–1625.
11. Kotov, A., Pospelov, P. (2017) Engineering Tools and Methods of Estimation of Traffic Capacity
Using Mobile Video Monitoring. Transp. Res. Procedia, 20, pp. 347–354.
12. Makino, H., Tamada, K., Sakai, K., Kamijo, S. (2018) Solutions for urban traffic issues by ITS
technologies. IATSS Res., 42(2), pp. 49–60.
13. Nagy, A. M., Simon, V. (2018) Survey on traffic prediction in smart cities, Pervasive Mob.
Comput., 50, pp. 148–163.
14. Aibin, M. (2018) Traffic prediction based on machine learning for elastic optical networks. Opt.
Switch. Netw., 30, pp. 33–39.
15. Rabbouch, H., Saâdaoui, F., Mraihi, R. (2018) A vision-based statistical methodology for
automatically modeling continuous urban traffic flows. Adv. Eng. Informatics, 38, pp. 392–403.
16. Matsuoka, S. (2018) Traffic management project in Phnom Penh. IATSS Res., 42(4), pp. 180–189.
17. Mfenjou, M. L., Abba Ari, A. A., Abdou, W., Spies, F., Kolyang (2018) Methodology and trends for
an intelligent transport system in developing countries, Sustain. Comput. Informatics Syst., 19,
pp. 96–111.
11. Transport and Telecommunication Vol. 22, no.1, 2021
97
18. Zhang, H., Dai, G. L. (2018) Research on traffic decision making method based on image analysis
case-based reasoning. Optik (Stuttg)., 158, pp. 908–914.
19. Małecki, K., Iwan, S. (2019) Modeling traffic flow on two-lane roads with traffic lights and
countdown timer, Transp. Res. Procedia, 39, no. 2018, pp. 300–308.
20. Dodsworth, Joel Andrew (2018) The application of vehicle classification, vehicle-to-infrastructure
communication and a car-following model to single intersection traffic signal control, Ph.D. thesis,
University of Leeds.