Enhanced RealTime Crowd Counting UsingYOLOv8 and DeepSORT Optimization.

Read full text Summarise with VIRAT
Authors: Abhijeet More, Sanika Keni Dept., Sumedh Jadhav Dept., Aditya Thorve Dept
Cited by: 0
References: 11

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Real-time detection of crowds in urban and public spaces has become increasingly important for public safety, security, and traffic movement due to the large number of people congregating at transport hubs, shopping malls, stadiums, and public gatherings.This paper proposes a Crowd Detection and Density Estimation System based on state-of-theart deep learning and computer vision techniques that can detect, analyze and quantify the density of crowds using live CCTV camera footage.The proposed approach uses a YOLO based object detection algorithm for real-time detection of persons in the scene, due to its high accuracy and low latency performance.In combination with the proposed frame extraction and preprocessing techniques, the proposed approach is highly effective in recognizing people in real-time in highly dynamic, cluttered and complex environments.The system can identify people, calculate crowd density levels, and classify them into low, moderate, and high density

Fields of Study & Subjects

Video Surveillance and Tracking Methods Advanced Neural Network Applications Evacuation and Crowd Dynamics

Publication details

Journal / source
International Journal for Research Trends and Innovation
Volume
11
Issue
3
Publication date
1 January 2026
Language
EN