A cross-camera pedestrian trajectory tracking method in shopping mall environment
Zhenxin Cao, Di Niu, Hailiang Gong, C. Shi, G. Zhang, Y. Yang · IET conference proceedings. · 2023
Pedestrian trajectory in the shopping mall environment plays an important role in criminal investigation, passenger flow statistics, big data recommendation and many other fields. In this paper, a pedestrian trajectory tracking method is proposed, which is based on artificial intelligence algorithms. The method is composed of three modules. First, YoloX is applied to detect pedestrians; secondly, the BYTE algorithm is applied to track pedestrians; finally, the FastReID network and matching algorithms are applied to identify pedestrians. In addition, we also use the BrainFrame platform to package and deploy the algorithm. Experiments show that this method can effectively perform person re-identification tasks with low performance requirements, thus contribute to pedestrian trajectory tracking task in shopping mall environment.