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{197288,
        author = {Darshan B M and Madan Kumar A S and Manoj H N and Namitha A R},
        title = {Animal Intrusion Detection in Farm lands Using CCTV},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {11391-11398},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197288},
        abstract = {Timely prevention of unexpected animal incursions into agricultural fields can be a significant challenge. Overall crop damage and threats to livestock often result from unexpected animal incursions into these types of fields, requiring the use of traditional prevention methods (manual surveillance, fencing, basic alarm systems, etc.), which can be ineffective, time-consuming and unreliable depending on the environmental conditions. The purpose of this paper is to present a new artificial intelligence-based system designed specifically for detecting animal incursions in agricultural fields by using cutting-edge computer vision and deep learning technologies. These technologies will be used to enable real-time surveillance of agricultural land through the use of CCTV or webcam video feeds and state-of the-art object detection models, such as YOLO and Faster R-CNN, which will provide a way to accurately detect, identify and track animals. The proposed solution is expected to provide users with an intuitive web-based interface that will allow them to upload video feeds, define regions of interests (ROIs) and view detected animal incursions in real-time. The system will notify users (through real-time alerts) when an animal incurs into a defined ROI so that timely action can be taken by users to prevent any future damages to crops/livestock. The proposed solution will also provide additional functionalities through use of computer vision-based preprocessing techniques, data logging and analytics facilitating better detection of animal incursions and enabling longer-term surveillance of the agricultural site. Based on the results of the experimental studies, the proposed solution has demonstrated a relatively high level of detection accuracy and a relatively low level of false alarms and, therefore, is deemed appropriate for deployment on agricultural properties. The proposed solution additionally offers users with a scalable, cost-effective, automated approach to securing their agricultural properties while contributing to sustainable agriculture and reducing incidences of conflict between humans and wildlife on farm properties.},
        keywords = {Animal Intrusion Detection, Computer Vision, Deep Learning, YOLO, Faster R-CNN, Object Detection, Smart Agriculture, CCTV Surveillance, Real-Time Monitoring, Image Processing, Precision Farming, Artificial Intelligence.},
        month = {April},
        }