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{195254,
        author = {Kalyani Pawar and Isha Mohite and Sakshi More and Yash Thakare and Mrs. Priti Malkhede},
        title = {Developing Surveillance System using Deep Sort and YOLOV8},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {7634-7637},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195254},
        abstract = {This review paper explores recent advancements in AI based smart surveillance systems designed for real time crowd monitoring, missing person detection, and abnormal behavior analysis [18], [20]. With increasing public safety concerns in crowded environments such as airports, railway stations, malls, and smart cities, traditional manual surveillance methods have become ineffective and error prone[2]. Modern surveillance systems leverage deep learning algorithms such as YOLO for object detection, Deep SORT for multi object tracking, and CNN VideoMAE models for behavioral analysis to automatically monitor live video feeds and generate real time alerts [7], [9], [15]. This paper reviews existing methodologies, models, system architectures, and datasets used in smart surveillance, highlighting their strengths and limitations [18]. Key challenges such as real time processing, scalability, data privacy, and environmental variations are also discussed [17], [19], [20]. The study provides insights into future research directions focusing on accuracy improvement, system scalability, and ethical surveillance deployment [19], [30].},
        keywords = {Smart Surveillance System, Deep Learning, YOLO, Object Detection, Behavior Analysis, Crowd Monitoring},
        month = {March},
        }