2. INTRODUCTION
Camera traps provide a low-cost approach to collect data and monitor wildlife across
large scales but hand-labeling images at a rate that outpaces accumulation is difficult
Deep learning, a subdiscipline of machine learning and computer science, can address the
issue of automatically classifying camera-trap images with a high degree of accuracy.
In this study, we propose to go even further by using object detection model to detect and
classify species on camera traps videos and alerting the local guards when it detects.
3. PAPER TITLE PUBLICATION ALGORITHM KEY FINDINGS
Detection of Wildlife
Animals using Deep
Learning Approaches: A
Systematic Review
2021 21st International
Conference on Advances in
ICT for Emerging Regions
(ICter)
VGG-16, YOLO V5 This paper examines the
major deep learning ideas
relevant to the detection
and recognition of wildlife
animals,
Identification of Wild
Species in Texas
from Camera-trap Images
using Deep Neural Network
for Conservation Monitoring
2020 10th Annual Computing
and Communication
Workshop and Conference
(CCWC)
YOLO V1, CNN This paper proposes an
automated wildlife
monitoring system by
image classification using
computer vision
algorithms and machine
learning techniques.
LITERATURE
REVIEW
4. PROPOSED SYSTEM
In this work, we focus on utilizing deep learning based approaches for object detection to identify
and localize animal species within camera trap images and alerting the local guard.
Camera trap data provides a robust measure of the capabilities of deep learning for species
classification, as the images are often ‘messy’, with animals being partly obstructed, positioned at
varying distances, cropped out of the image, or extremely close to the camera.
In our system it is capable of accurately classifying more than one species per image given limited
data when utilizing transfer learning.
5. VGG16 (VISUAL GEOMETRY GROUP)
VGG-16 is a convolutional neural network that is 16 layers deep.
You can load a pretrained version of the network trained on more than a million images from the
ImageNet database
The pretrained network can classify images into 1000 object categories, such as keyboard, mouse,
pencil, and many animals.
6. YOLO — YOU ONLY LOOK ONCE
The Long-Short-Term Memory is a type of Recurrent Neural Network or RNN..
LSTMs are used as they have been designed to work with time series data and have shown great
results when used for classification and prediction in sequential data such as videos.
It excels at capturing long-term dependencies, making it ideal for sequence prediction tasks.
7. FAST R-CNN
Faster R-CNN is a deep convolutional network used for object detection, that appears to the user
as a single, end-to-end, unified network.
Faster R-CNN shows promise for accurate and autonomous analysis of camera trap data,
The Faster R-CNN utilizes is a two-stage deep learning object detector: first, it identifies regions
of interest and then passes these regions to a convolutional neural network. The outputted feature
maps are passed to a support vector machine (SVM) for classification.
9. CONCLUSION
Camera traps provide a critical aid in multifaceted surveys of wildlife worldwide while they often
produce large volumes of images and videos . A growing number of studies have tried to use deep
learning techniques to extract effective information from massive images or videos
A key advantage lies in the precise identification of animals. Based on the outcomes documented
in the scrutinized research papers, yolov3 demonstrates exceptional accuracy in animal
identification
10. REFERENCE
Falzon, G., Lawson, C., Cheung, K.-W., Vernes, K., Ballard, G.A., Fleming, P.J.S. et al. (2020) ClassifyMe: a field-
scouting software for the identification of wildlife in camera trap images. Animals, 10(1), 58. Available
from: https://doi.org/10.3390/ani10010058
Mina Gabriel, Sangwhan Cha, Nushwan Yousif B. Al-Nakash, and Daqing Yun Wildlife Detection and Recognition
in DigitalImages Using YOLOv3,15 Dec.2020
Abhijeet Singh , Marcin Pietrasik , Gabriell Natha , Nehla Ghouaiel , Ken Brizel, Nilanjan Ray. Animal Detection
in Man-madeEnvironments, 2020.
R. Shanthakumari,C. Nalini,S. Vinothkumar,B. Govindaraj. Image Detection and Recognition of different species
of animals using Deep Learning ,April 2022.