Deep Learning Based on Crowd Monitoring using Yolo Algorithm

Authors: Payal Balasaheb Lawand, Mrunali Randhir Khairnar, Kalyani Sunil Shelke, Vijaya Pundalik Nikam, Priyanka P. Kakade

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: Effective crowd management is essential for ensuring public safety in large gatherings. Traditional deep learning approaches for crowd analysis, including people counting, detection, and movement tracking, often require high computational resources, making them unsuitable for real-time applications on edge devices. This paper presents a Convolutional Neural Network (CNN)-based model designed to efficiently process crowd data while optimizing computational and memory demands. The proposed system enables real-time people detection, tracking, and movement estimation, allowing authorities to monitor and manage crowds proactively. By leveraging lightweight deep learning techniques, the model ensures high accuracy while maintaining efficiency, making it suitable for smart surveillance and public safety applications.

Keywords: Crowd Management, Real-Time Crowd Analysis, People Detection, Tracking, Convolutional Neural Network (CNN), Edge Computing, Deep Learning, Movement Estimation, Smart Surveillance, Public Safety.

Paper Id: 233082

Published On: 2026-04-27

Published In: Volume 14, Issue 2, March-April 2026

Share this