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 | To Implement Deep Learning -Based Real Time Crowd Monitoring and Density Estimation System |
|---|---|
| ABSTRACT | This project presents a real-time crowd monitoring and density analysis system using YOLOv8 deep learning model and computer vision techniques. The system analyse uploaded images, live video streams, and webcam feeds to detect persons, calculate crowd density, and assess safety risks. A Crowd Stress Index (CSI) is generated based on person count and spatial distribution to classify risk levels as Safe, Crowded, or Dangerous. The system enables adaptive monitoring, alert generation, and historical data logging for event management and public safety applications. This approach promotes intelligent crowd management, reduces manual monitoring overhead, and enhances safety in public spaces like malls, stadiums, transportation hubs, and educational institutions. Machine learning and computer vision provide automated solutions for real-time person detection, density analysis, and risk assessment. Deep learning models like YOLO (You Only Look Once) enable accurate object detection in crowded environments. This approach promotes intelligent crowd management, reduces manual monitoring overhead, and enhances safety in public spaces like malls, stadiums, transportation hubs, and educational institutions. |
| AUTHOR | EZHILARASI.S, SHALINI V, DEVADHARSHINI C, KARTHIGAYINI M Assistant Professor, Department of Computer Science and Engineering, P.S.V College of Engineering and Technology, Mittapalli, Krishnagiri, India. UG Scholar, Department of Computer Science and Engineering, P.S.V College of Engineering and Technology, Mittapalli, Krishnagiri, India |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404043 |
| pdf/43_To Implement Deep Learning -Based Real Time Crowd Monitoring and Density Estimation System.pdf | |
| KEYWORDS | |
| References | [1] Redmon, J., & Farhadi, A., “YOLOv3: An Incremental Improvement,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [2] Jocher, G., “Ultralytics YOLOv8 Object Detection,” GitHub Repository, 2023. [3] Zhang, Y., Zhou, D., “Deep Learning for Crowd Counting: A Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023. [4] OpenCV Documentation, “OpenCV Computer Vision Library,” opencv.org. [5] Flask Documentation, “Flask Web Framework for Python,” flask.palletsprojects.com. [6] OpenCV Documentation, “OpenCV Computer Vision Library,” Available at: opencv.org. Official documentation for OpenCV used in image and video processing. [7] Flask Documentation, “Flask Web Framework for Python,” Available at: flask.palletsprojects.com. Provides guidance for building web applications and dashboards using Flask. [8] Patel, R. et al., “Grid-Based Crowd Density Estimation Using Computer Vision,” International Journal of Computer Applications, 2021. Explains grid-based methods for estimating crowd density. [9] Smith, J., Brown, A., “Real-Time Video Processing for Crowd Monitoring,” Journal of Visual Communication, 2023. Focuses on techniques for real-time video analysis in surveillance systems. [10] Goodfellow, I., Bengio, Y., Courville, A., “Deep Learning,” MIT Press, 2016. A foundational book covering concepts and techniques in deep learning. |
