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{200297,
        author = {Saish Vikrant Wader and Komal Shrinivas Yangal and Nikunj Mukul Wandile and Pratishtha Satish Mane and Rutuja Uday Khandagale and Prashantkumar M. Gavali},
        title = {AI-Driven Real-Time Weapon Detection for Anti-Poaching Surveillance Using YOLOv8},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {4125-4128},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200297},
        abstract = {Poaching is a significant threat to wildlife particularly in forests. The conventional methods of surveillance have the problem of low visibility, geographical coverage and slow human response. In this paper, an anti-poaching surveillance system of an AI based real time weapon detection system is presented using the YOLOv8 model. The system examines live video streams of CCTV and IP cameras, uses preprocessing (CLAHE enhancement, Gaussian denoising) to enhance the quality of images in low-light and covered areas, and detects weapons like guns and knives. When detected, real time alerts are sent through SMS/email and stored in PostgreSQL database. Experimental findings on a custom forest dataset (2,500 annotated images) show results of 80% accuracy, 83 percent precision, 84 percent recall and 91.2 mAP/0.5 on NVIDIA GTX 1080 Ti GPU. When compared to YOLOv5 and Faster R CNN, it can be determined that the best tradeoff between speed and accuracy in this application is with YOLOv8. The system lessens the use of manual patrolling and reduces the response time by the forest authority.},
        keywords = {Forest surveillance, weapon detection, YOLOv8, deep learning, computer vision, real time alerting.},
        month = {May},
        }