Abstract
Crowd detection has recently been a critical issue in machine vision. In response to the recent epidemics' impact, people tend to avoid crowded places, such as markets and bazaars. Crowd analysis can significantly solve this issue and help epidemic prevention. In this study, we proposed a deep learning-based crowd-tracking system using YOLOv5 with StrongSort and OSNet for detection and analyzing the obtained data, such as crowd tracking, counting and plotting crowd trajectories, and motion maps, and hotspot maps to analyze crowding levels. Regarding data training, we use LabelGo for semi-automatic annotation and training. We also tested the size of the pixels that can detect the smallest object (1.0 x 20.0 pixels) and the effect of the number of people on the screen on the time we spent detecting, tracking, and plotting. The detection, tracking, and plotting time is less than 3 seconds for a crowd of more than 100 people, so the results can be presented quickly.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
