NOVEL ANIMAL DETECTION SYSTEM USING IMPROVED YOLO
DOI:
https://doi.org/10.5281/zenodo.21102217Abstract
Wild animal intrusion in residential areas and sudden road crossings pose significant risks to both humans and wildlife. Leveraging advanced technologies, this research proposes a reliable wildlife detection system based on a cascaded YOLOv11 approach. The system plays a crucial role in monitoring biodiversity, understanding animal behaviour, and supporting global conservation efforts. To enhance detection accuracy, the input dataset is pre-processed using adaptive histogram equalization for contrast enhancement. Following this, segmentation is performed using a super-pixel-based Fast Fuzzy CMeans (FCM) clustering technique to identify regions of interest. Features are subsequently extracted and fed into the cascaded YOLOv11 framework for accurate detection and classification of wild animals. The proposed approach ensures robust and efficient wildlife monitoring, offering a valuable solution to mitigate human-wildlife conflicts while contributing to environmental sustainability and wildlife conservation.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.













