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{207958,
        author = {Siddaraju K and Anil Kumar R J and Nirmala M S and Nagendra Nath Giri},
        title = {Smart Surveillance System for Unauthorized Individual Detection Using YOLO, FaceNet, and ByteTrack},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {3761-3773},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207958},
        abstract = {This paper proposes an integrated AI-based smart surveillance system to identify unauthorized people in real-time using unified deep learning techniques. In this paper, we developed AI-based smart surveillance architecture that integrates YOLOv8 for object detection, Byte Track for robust multi-object tracking, and MTCNN-Face Net as a combination of facial recognition techniques. We successfully integrated these techniques to obtain optimal results in detecting human beings, tracking, and facial recognition. We used live video streaming as input, and throughout the paper, we demonstrated that the proposed method can be used for real-time facial recognition systems. We used WIDER Face, LFW, and other datasets to conduct experiments on a unified platform. We found that the proposed Object Detection module can achieve more than 96% of average precision in mean Average Precision (mAP). In comparison, byte track module can achieve over 92% Multiple Object Tracking Accuracy (MOTA). We also achieved up to 99.5% on LFW and over 94% on real-world scenarios for facial recognition techniques, respectively. We estimated that the AI-based smart surveillance system can work between 17 and 25 frames per second, respectively, using GPU acceleration. Hence, in conclusion, we can say that AI-based smart surveillance can be used for multiple scenarios, such as airports,},
        keywords = {YOLOv8, Face Net, MTCNN, Byte Track, Face Recognition, Object Detection, Real-Time Surveillance, AI Security Systems.},
        month = {August},
        }