International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Crowd Guard AI: Predictive Crowd Safety Intelligence System |
|---|---|
| ABSTRACT | Given the quick increase in urban populations and large-scale public gatherings, ensuring crowd safety has become a critical challenge. Incidents such as overcrowding, stampedes, and panic situations often arise as a result of the absence of real-time monitoring and predictive analysis in traditional surveillance systems. Existing methods mainly rely on manual observation of CCTV footage, which is inefficient, error-prone, and incapable of providing early warnings. This project, Crowd Guard AI: Predictive Crowd Safety Intelligence System, proposes an advanced AI-powered system that incorporates computer vision, deep learning, and real-time analytics to enhance crowd monitoring and safety. The system utilizes state-of-the-art models such as YOLO for human detection and Deep SORT for multi-object tracking across multiple camera feeds. It further incorporates machine learning techniques to analyse crowd density, detect abnormal movement patterns, and identify panic behaviour in real time. Additionally, the system generates dynamic crowd density heatmaps and provides predictive insights to foresee possible dangers before they become more serious. A Flask-based web dashboard is developed to visualize crowd conditions, track individuals, and deliver instant alerts to authorities. This enables faster decision-making and proactive crowd control measures. |
| AUTHOR | DARSHAN M S, NASEERHUSEN ANKALAGI PG Student, Dept. of MCA, City Engineering College, Bengaluru, Karnataka, India Assistant Professor, Dept. of MCA, City Engineering College, Bengaluru, Karnataka, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405050 |
| pdf/50_Crowd Guard AI Predictive Crowd Safety Intelligence System.pdf | |
| KEYWORDS | |
| References | 1. M. S. Janardhana Reddy, A. C. Kowshik, and C. R. Sharma, “Crowd control and monitoring using deep learning,” in Proc. 2024 2nd Int. Conf. Networks, Multimedia and Information Technology (NMITCON), 2024, pp. 1–6. 2. M. Saleem, A. Khan, and R. Ullah, “Real-time crowd behavior tracking using hybrid CNN–Transformer models,” Pattern Analysis and Applications, vol. 27, no. 2, pp. 1–15, 2024. 3. K. Raj and S. Nambiar, “AI-driven urban crowd flow prediction using multi-modal data,” Information Fusion, vol. 102, pp. 120–132, 2024. 4. M. A. Khan, S. Rehman, and T. Hussain, “Crowd counting at the edge using knowledge distillation,” Scientific Reports, vol. 15, pp. 1–12, 2025. 5. M. J. Asif, “Crowd scene analysis using deep learning techniques,” arXiv preprint arXiv:2505.08834, 2025. 6. S. Lashari, M. Ahmed, and K. Shah, “AI and IoT-based frameworks for real-time crowd monitoring and security,” IEEE Access, vol. 13, pp. 1–15, 2025. 7. S. Kumar, R. Gupta, and P. Singh, “Real-time crowd monitoring and management using computer vision,” in Proc. IEEE Int. Conf. Smart Systems, 2025, pp. 45–50. 8. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, real-time object detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 779–788. |
