Pedestrian Angle Recognition Based on JDE Multi-object Tracking Algorithm

Abstract

We often execute multi-object tracking algorithms and pedestrian angle recognition algorithms independently when we solve complex problems that need to track multiple pedestrians and identify their angles simultaneously. Firstly, the multi-target tracking algorithm is used to locate the target and determine the target’s identity. Then the pedestrian angle recognition model is used to recognize the pedestrian angle. This strategy is complicated and inefficient since the two models repeatedly extract target features. This paper realizes the combination of multi-object tracking algorithm and pedestrian angle recognition algorithm in response to this problem. Specifically, we added a new classification branch based on the JDE multi-object tracking algorithm. It enables the model to perform pedestrian angle recognition while detecting and embedding feature extraction. Finally, experiments show that the improved algorithm can perform pedestrian tracking and pedestrian angle recognition simultaneously. The algorithm’s ability to track large and medium targets is the same as the JDE multi-object tracking algorithm. Compared with the Hydraplus model, the improved algorithm has a higher recognition accuracy. Besides, the algorithm can achieve real-time performance.