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{194387,
        author = {Krishna Veni Ampolu},
        title = {An AI-Powered Intelligent CCTV Surveillance System for Detecting Violence, Accidents, and Weapon Threats Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {4635-4642},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194387},
        abstract = {In the present digital era, ensuring safety and security in public and private spaces has become a critical challenge due to the increasing number of crimes, violent incidents, and unexpected accidents. Surveillance systems such as Closed-Circuit Television (CCTV) cameras are widely deployed in areas like educational institutions, shopping malls, hospitals, transportation hubs, traffic intersections, and residential complexes. Although traditional CCTV systems are effective in recording events, they primarily depend on continuous human monitoring to identify suspicious or abnormal activities. The proposed solution employs action recognition models to analyse human behaviour and identify violent activities such as physical fights and abnormal movements that may indicate accidents. These models extract spatial and temporal features from video frames to understand motion patterns and interactions between individuals. In addition to action recognition, object detection algorithms are used to detect the presence of dangerous objects such as knives and firearms within the video frames. The proposed AI-powered CCTV system can be deployed in a wide range of applications, including public safety monitoring, traffic accident detection, crime prevention, and institutional security. By providing timely alerts and reducing the burden on human operators, the system enhances situational awareness and supports proactive security measures. Furthermore, the use of optimized deep learning models ensures that the system can be implemented using existing CCTV infrastructure without requiring excessive computational resources. In conclusion, this project aims to develop a robust, intelligent, and automated surveillance system that overcomes the limitations of traditional CCTV monitoring. By leveraging artificial intelligence, the proposed system improves detection accuracy, reduces response time, and enhances overall public safety. The implementation of such AI-based surveillance solutions represents a significant step toward smarter and safer environments in both public and private spaces.},
        keywords = {Artificial Intelligence, Computer Vision, Deep Learning, YOLO Algorithm, Object Detection, Fight Detection, Accident Detection.},
        month = {March},
        }