Volume 15, Issue 4

AI-Based Crowd Safety Monitoring in public Places

Author

Mrs M. Maheswari, Dhanusu K A, Dhayanand P, Gokul Raj A, Lokeshwaran N

Abstract

Rapid urbanization and the increasing frequency of large public gatherings have created significant challenges in ensuring public safety. Overcrowding in transportation hubs, stadiums, shopping centers, and event venues can lead to accidents, stampedes, and delayed emergency responses. Traditional crowd monitoring systems rely heavily on manual surveillance, which is inefficient, time-consuming, and prone to human error. This paper proposes an AI-based crowd safety monitoring system that uses computer vision and machine learning techniques to detect crowd density, analyze movement patterns, and identify abnormal behaviors in real time. The proposed system integrates surveillance cameras, intelligent data processing, and predictive analytics to enhance situational awareness and support timely decision-making. Experimental observations show that AI-driven monitoring significantly improves risk detection accuracy and response efficiency compared to conventional methods. The system can play a vital role in smart city infrastructure and public safety management.

REFERENCE

1. S. S. Khan and M. Shah, “A survey of crowd analysis methods,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 16, no. 12, pp. 1546–1560, Dec. 2006.
2. C. Zhang, H. Li, X. Wang and X. Yang, “Cross-scene crowd counting via deep convolutional neural networks,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 833–841.
3. A. B. Chan and N. Vasconcelos, “Counting people with low-level features and Bayesian regression,” IEEE Transactions on Image Processing, vol. 21, no. 4, pp. 2160–2177, Apr. 2012.
4. P. S. Sreelekha and M. Wilscy, “A computer vision based approach for crowd density estimation for public safety,” in Proc. International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 2018, pp. 1063–1067.
5. J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, real-time object detection,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 779–788.
6. H. Idrees, I. Saleemi, C. Seibert and M. Shah, “Multi-source multi-scale counting in extremely dense crowd images,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, USA, 2013, pp. 2547–2554.
7. V. A. Sindagi and V. M. Patel, “A survey of recent advances in CNN-based single image crowd counting and density estimation,” Pattern Recognition Letters, vol. 107, pp. 3–16, May 2018.

DOI

https://doi.org/10.62226/ijarst20262657

PAGES : 1905-1908 | 10 VIEWS | 6 DOWNLOADS

Download Full Article