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{188398,
        author = {Anuj Gadekar and Suraj Khairnar and Ayush Gaikwad and Shantanu Game},
        title = {AI-Based Real-Time Shoplifting Detection System Using Deep Learning and CCTV Footage},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {2457-2462},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188398},
        abstract = {Retail theft, specifically shoplifting, results in billions of dollars in losses annually. Traditional surveillance relies heavily on human monitoring, which is prone to fatigue and scalability issues. This paper proposes an automated, real-time shoplifting detection system utilizing a hybrid deep learning architecture. We employ the YOLOv8-Pose model to efficiently extract 17 skeletal keypoints for multi-person tracking and a Long Short-Term Memory (LSTM) network to classify temporal behavioral patterns. The system is designed to distinguish between normal shopping behavior and suspicious gestures, such as concealing items, without relying on facial recognition. Experimental results on a combined dataset of local and UCF Crime videos demonstrate an overall system accuracy of 80%, validating its feasibility as a privacy-preserving and cost-effective surveillance solution.},
        keywords = {Computer Vision, Deep Learning, LSTM, Shoplifting Detection, YOLOv8-Pose.},
        month = {December},
        }