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{198202,
        author = {Arul kumar S and Gowtham M and Nithish R and Vigneshwaran R and Mahavishnu c and Kanmani G and Dr k Sasikala},
        title = {Intelligent Weapon Detection System for Real-Time Surveillance using Deep Learning with YOLOv8},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {9097-9106},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198202},
        abstract = {Public safety has become an important concern in modern society due to the increasing number of violent incidents in public environments such as transportation hubs, educational institutions, and commercial areas, while traditional surveillance systems rely heavily on continuous human monitoring, leading to delayed responses and reduced efficiency. To address this limitation, this research proposes an Intelligent Weapon Detection System for real-time surveillance using deep learning with YOLOv8. The system utilizes advanced computer vision techniques to automatically detect weapons such as guns and knives from live CCTV video streams, where video frames are captured, preprocessed through resizing, normalization, and noise reduction, and analyzed using the YOLOv8 model for accurate and fast detection. The model extracts spatial features and identifies weapons using bounding boxes and confidence scores, while techniques such as confidence thresholding and Non- Maximum Suppression are applied to improve detection reliability and reduce duplicate predictions. Upon detection, the system generates alerts and stores relevant data for monitoring and analysis. The proposed system integrates video capture, frame extraction, preprocessing, feature extraction, object detection, and alert generation into a unified automated pipeline, enhancing surveillance efficiency, enabling rapid threat identification, reducing manual effort, and allowing deployment on edge devices and existing infrastructure without specialized hardware, thereby improving situational awareness and strengthening public safety systems. This approach also supports scalability and future integration with smart city surveillance enhanced security.},
        keywords = {Intelligent Surveillance, Weapon Detection, YOLOv8, Deep Learning, Computer Vision, Real-Time Monitoring, Object Detection, Public Safety, Threat Detection, Smart Security Systems, Artificial Intelligence.},
        month = {April},
        }