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{189013,
        author = {Divyam Jangada and Yashraj Nikam and Aditya Lagad and Palak Chawarkar},
        title = {Drishti: An AI-Powered Gesture-Based Crowd Safety System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4857-4860},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189013},
        abstract = {Mass gatherings such as religious festivals, political rallies, and concerts in India often attract millions of people, posing serious risks of overcrowding and stampedes. Despite the availability of CCTV surveillance, the absence of real-time automated monitoring for distress gestures, abnormal motion, and panic cues leads to delayed responses and preventable accidents. This paper presents 'Drishti', an AI-powered gesture-based crowd safety system that integrates computer vision and audio analysis to detect unsafe crowd behaviors in real time. The system employs deep learning models for gesture recognition, crowd density analysis, and panic audio detection using datasets such as UCF Crowd and ShanghaiTech. The integrated alert mechanism notifies authorities through IoT-enabled systems to ensure rapid intervention. Results demonstrate the feasibility of this system in enhancing public safety through early warning and predictive analytics during large-scale events. Future enhancements include IoT integration, emotion recognition, and multilingual alert systems for improved adaptability.},
        keywords = {AI Surveillance, Gesture Recognition, Crowd Safety, Panic Detection, Deep Learning, Audio Analysis, IoT Alerts, Computer Vision, Crowd Monitoring.},
        month = {December},
        }