Aditya Sharad Somwanshi
Pratik Tukaram Rahinj
Alisha Rajmohammad Shaikh
D. M. Bhalerao
- Student, Department of Electronics & Communication Engineering, Sinhagad College of Engineering Vadgaon (BK), Pune, Maharashtra, India
- Student, Department of Electronics & Communication Engineering, Sinhagad College of Engineering Vadgaon (BK), Pune , Maharashtra, India
- Student, Department of Electronics & Communication Engineering, Sinhagad College of Engineering Vadgaon (BK), Pune , Maharashtra, India
- Assistant Professor, Department of Electronics & Communication Engineering, Sinhagad College of Engineering Vadgaon (BK), Pune , Maharashtra, India
Abstract
This study focuses on teaching a computer to identify leopards in images through a process called Object Detection and Image Recognition. We created a special set of pictures (dataset) containing thousands of leopard images. Using a small camera module called ESP32 CAM, we trained the computer to recognize leopards by comparing the images it captures with the ones in the dataset. The results were obtained using a Convolutional Neural Network (CNN). Leopards are elusive creatures, and accurately identifying them in images can be challenging due to their camouflaged coats and the diverse environments they inhabit. Existing methods might not be efficient or portable, often requiring expensive equipment and extensive manual labour. By leveraging the ESP32 CAM, a cost-effective and compact solution, we can deploy this technology in remote and rugged terrains, making it accessible for widespread use. This survey can be particularly useful for wildlife conservation efforts, helping researchers monitor leopard populations more effectively. A system that recognizes the presence of animals and alerts people to it is necessary for security reasons since animals that invade agricultural regions close to forests can damage crops or even attack humans. This page identifies wild animals that penetrate human habitation. Automated leopard detection can enhance data collection accuracy, reduce human error, and allow for real-time monitoring. This technology can also assist in identifying individual leopards based on their unique spot patterns, aiding in population tracking and behavioural studies.
Keywords: CNN, Object detection, Image Recognition, ESP32, Tensor Flow
[This article belongs to Journal of Microwave Engineering and Technologies(jomet)]
References
] B. Natarajan, R. Elakkiya, R. Bhuvaneswari, Kashif Saleem, Dharminder Chaudhary, Syed Husain, Samsudeen, “Creating Alert Messages Based on Wild Animal Activity Detection Using Hybrid Deep Neural Networks”, IEEE,2023.
[2] Ibraheam M, Li KF, Gebali F. An accurate and fast animal species detection system for embedded devices. IEEE Access. 2023 Mar 3; 11:23462-73.
[3] Davide Adami, Mike O. Ojo, Stefano Giordano, “Design, Development and Evaluation of an Intelligent Animal Repelling System for Crop Protection”, IEEE, 2021. International Research Journal of Engineering and Technology (IRJET) vol. 07, issue 03, Mar 2020
[4] Girish H, Manjunat TG, Vikramathithan AC. Detection and Alerting Animals in Forest using Artificial Intelligence and IoT. In2022 IEEE Fourth International Conference on Advances in Electronics, Computers and Communications (ICAECC) 2022 Jan 10 (pp. 1-5). IEEE.
[5] N. Nandhini, S.V. Jeyasri, R. Logapriya, B. Shubeeksha Raja Shri4, A Survey on Object Detection for Animal Detection and Prevention in Agricultural Field Using IoT, ISSN 2582-7421, International Journal of Research Publication and Reviews, Vol 4, no 3, pp 2770-2773, March 2023
[6] KEERTHANA S, SHYLA DE. A LITERATURE SURVEY ON WILD ANIMAL DETECTION USING VARIOUS DATAMINING TECHNIQUES. IJRAR-International Journal of Research and Analytical Reviews (IJRAR). 2018 Aug;5(3):616-22.
[7] Prasham Mehta, Keval Shah, Rohit Raval, Manan Shah, Wildlife Identification using Object Detection using Computer Vision and YOLO, International Research Journal of Engineering and Technology (IRJET) , Volume: 10 Issue: 08
[8] Hossain MZ, Sohel F, Shiratuddin MF, Laga H. A comprehensive survey of deep learning for image captioning. ACM Computing Surveys (CsUR). 2019 Feb 4;51(6):1-36.
[9] Bakana SR, Zhang Y, Twala B. WildARe-YOLO: A lightweight and efficient wild animal recognition model. Ecological Informatics. 2024 May 1; 80:102541.
[10] Niu Y, Wang Z. Research on Object Detection in Animal Images Based on Convolutional Neural Networks. International Journal of Advanced Network, Monitoring and Controls.;8(4):45-54
Journal of Microwave Engineering and Technologies
| Volume | 14 |
| Issue | 01 |
| Received | May 23, 2024 |
| Accepted | June 4, 2024 |
| Published | June 14, 2024 |