Design and Implementation of the Pedestrian Information Analysis System
Wenli Zhang, Kun Yang, Xiang Guo · IOP Conference Series Materials Science and Engineering · 2018
In this paper, we proposed a pedestrian information analysis system. It is consisted of the pedestrian detection module and the pedestrian tracking module. Compared with various pedestrian detection methods, the Deformable Part Model (DPM) algorithm is used to detect the pedestrians in the picture. Meanwhile, this paper proposes a pedestrian tracking method. This method uses the pedestrian detection result to calculate the pedestrian's centroid and uses the video time domain information to track the centroid. It can help us to obtain the pedestrian information that includes the pedestrian moving distance and direction. We set the count line to count the pedestrian's number and direction in this system. The experiment results show that the system we proposed can analyse pedestrians more accurately.