Copyright © 2025 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{181464,
        author = {Suraj R. Sanap and Utkarsh P. Singh and Niranjan N. Patil and Prof. Rahul M. Samant},
        title = {IndShield: Comprehensive Computer Vision System for Real-Time Safety Surveillance},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {5050-5053},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181464},
        abstract = {This paper presents IndShield, an integrated real-time safety surveillance system that leverages advanced computer vision and deep learning techniques to detect and respond to multiple safety hazards simultaneously. The proposed solution encompasses five critical modules: fire detection, personal protective equipment (PPE) compliance verification, restricted zone intrusion monitoring, emergency pose detection, and motion amplification. By employing state-of-the-art models such as YOLO for object detection and MediaPipe for pose estimation, IndShield delivers highaccuracy detection with minimal latency. A Flask-based web interface enables centralized monitoring and management, while the Twilio API ensures real-time SMS alerts to designated personnel. Experimental evaluations demonstrate superior detection accuracy, low false-positive rates, and robust performance under diverse operational conditions. IndShield’s unified architecture significantly enhances situational awareness, making it a practical solution for industrial and public safety environments.},
        keywords = {YOLO, MediaPipe, Fire Detection, PPE Compliance, Intrusion Monitoring, Pose Estimation, Motion Amplification},
        month = {June},
        }