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{199394,
        author = {Vishesh Panwar and Dr. Ritu Gautam},
        title = {AI-Powered Smart Surveillance for Real-Time Multi-Threat Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {13045-13050},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199394},
        abstract = {Classical surveillance infrastructure depends on active monitoring of people by humans, which is inefficient, has errors, and is inappropriate on large scales. As the number of security threats, accidents, and environmental hazards in the community continues to rise, the need to adopt intelligent surveillance systems with the capability of detecting threats in real time has risen. This article proposes an AI-enhanced smart surveillance system that is founded on YOLOv8 to detect weapons, fire, and accidents in real-time. This recommended system is centered around using an object detector system founded on deep learning that would analyze live videos, detect objects posing danger, and provide alerts with little delay. YOLOv8 will be chosen for this purpose because of its single-stage approach which achieves the optimal balance between the detection rate and real-time execution. Exploratory study and comparative sensitivity with the existing solutions show that the proposed system improves situational awareness, response time, and scalability of smart public safety monitoring.},
        keywords = {Smart Surveillance, YOLOv8, Real-Time Object Detection, Multi-Threat Detection, Computer Vision.},
        month = {April},
        }