Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190570,
        author = {Dr. M. Sindhana Devi and Devadarshini P and Midhunesh G},
        title = {Edge-AI for Ecology: YOLOv8-Based Smart Wildlife Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {4451-4454},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190570},
        abstract = {Wildlife tracking is of particular importance for biodiversity protection and environmental management. Conventional manual processes are time-consuming and susceptible to human mistakes. The current project proposes a deep learning-based wildlife detecting framework using the YOLOv8 object detection mechanism. The model is trained on a well-prepared wildlife dataset of annotated species pictures to allow precise real-time identification. Training was done for 25 epochs, with a batch size of 16 and a resolution of the images to 640×640. The model showed strong learning capabilities, with accurate object localization and classification across species classes. The detection pipeline utilizes OpenCV for visualization, with bounding boxes, confidence, and class labels overlaid onto test images. The model was tested with YOLOv8's evaluation metrics, which provided robust performance in mean Average Precision (mAP) and inference speed. The output images demonstrate efficient species detection, which can significantly support automated monitoring, anti-poaching monitoring, and ecological study. The lightweight nature of the system allows it to be adaptable for deployment on drones, camera traps, or embedded systems, both for research and field use. In general, the project emphasizes the real-world application of deep learning for monitoring and conservation of wildlife.},
        keywords = {YOLOv8, Object Detection, Deep Learning, Wildlife Monitoring, Computer Vision, Conservation Technology, Python, OpenCV, PyTorch.},
        month = {January},
        }