Enhanced RealTime Crowd Counting UsingYOLOv8 and DeepSORT Optimization.

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 Besides, the execution of manual monitoring may bring delays and inconsistencies, especially in large facilities.With the help of computer vision and deep learning, automated crowd detection systems are a faster, more robust solution that can reduce human error and increase situation awareness.This project presents a real, time Crowd Detection System that is based on the YOLO deepU