Enhancing Animal repellent system using AI and Deep Learning

DOI

10.2991/978-94-6463-718-2_93How to use a DOI?

Keywords

Wildlife monitoring; animal detection; yolov5 model; deep learning techniques

Abstract

The goal is to design a real-time animal incursion detection system based on the YOLOv5-based model to promote wildlife monitoring using image data and accurately detect animal presence. This technique utilizes deep learning along with YOLOv5 architecture known mostly for its efficient performance in object-identifier tasks. As the structured format of the data reflects on training stage, the very first thing to do here is creating the dataset (that zip file), which includes unzipping and ordering the picture files. During the model training process, the model is fine-tuned with the following important parameters to achieve the best detection performance on epoch, batch size and image size. A configuration file called model. The yaml file basically tells the system how to train so it can detect thousands of different types of animals. Then, the machine learning system is trained over a handful of well-chosen samples of the images and, depending on a confidence threshold, a carefully filtered detection for an animal incursion is identified. Here, we visualize the results with OpenCV and Matplotlib which offers a comprehensive method of evaluating the accuracy of the model. Such a multi-faceted approach combines cutting-edge computational techniques to facilitate scalable and efficient detection and characterization of animal behavior across different settings.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - U. Kasthuri
AU  - P. Priyadharshini
AU  - R. Dhanush
AU  - P. S. Kavin Kumar
AU  - G. Madhu Nandha
AU  - M. D. Riyaz
PY  - 2025
DA  - 2025/05/23
TI  - Enhancing Animal repellent system using AI and Deep Learning
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 1106
EP  - 1113
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_93
DO  - 10.2991/978-94-6463-718-2_93
ID  - Kasthuri2025
ER  -