Although there is significant progress and wide applications in multi object tracking technology in recent years, the occlusion problem has always been an obstacle, especially in subway systems with dense crowds, high mobility, and narrow spaces. This difficulty greatly affects the accuracy of tracking and identification. Aiming at the problem of crowd occlusion in subway stations, based on the FairMOT [1], we improve the model and apply it to the subway so that it can count the number of people moving in different directions and enrich the data of pedestrian flow. However, FairMOT still cannot solve the occlusion problem in subway scenes because it cannot handle missing pedestrians effectively. Therefore, we propose three methods to solve the occlusion problem, including a new convolution branch, feature matching and handling of missing. Then, we show how to count the number of people moving in different directions. Experimental results demonstrate that our innovation can effectively improve the tracking performance not only in the case of short-distance double cross occlusion but also for long-distance dense crowd occlusion and building occlusion.
An Improved FairMOT Method for Crowd Tracking and Counting in Subway Passages
Lect. Notes Electrical Eng.
International Conference on Intelligent Transportation Engineering ; 2021 ; Beijing, China October 29, 2021 - October 31, 2021
2021 6th International Conference on Intelligent Transportation Engineering (ICITE 2021) ; Kapitel : 11 ; 130-139
01.06.2022
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
An Improved FairMOT Method for Crowd Tracking and Counting in Subway Passages
British Library Conference Proceedings | 2022
|Multi-view branch-shared subway platform crowd counting method
British Library Conference Proceedings | 2023
|Intelligent subway carriage with crowd density detection function
Europäisches Patentamt | 2020
|WiFi-Crowd Spy: A novel crowd-counting system
IEEE | 2022
|