Deep Alignment Network Based Multi-Person Tracking With Occlusion and Motion Reasoning

Abstract

Tracking-by-detection is one of the most common paradigms for multi-person tracking, due to the availability of automatic pedestrian detectors. However, existing multi-person trackers are greatly challenged by misalignment in the pedestrian detectors (i.e., excessive background and part missing) and occlusion. To address these problems, we propose a deep alignment network based multi-person tracking method with occlusion and motion reasoning. Specifically, the inaccurate detections are firstly corrected via a deep alignment network, in which an alignment estimation module is used to automatically learn the spatial transformation of these detections. As a result, the deep features from our alignment network will have a better representation power and thus lead to more consistent tracks. Then, a coarse-to-fine schema is designed for construing a discriminative association cost matrix with spatial, motion and appearance information. Meanwhile, a principled approach is developed to allow our method to handle occlusion with motion reasoning and the re-identification ability of the pedestrian alignment network. Finally, a simple yet real-time Hungarian algorithm is employed to solve the association problem. Comprehensive experiments on MOT16, ISSIA soccer, PETS09 and TUD datasets validate the effectiveness and robustness of the proposed method.