Structure and appearance preserving network flow for multi-object tracking

Shi Pu, Honggang Zhang, Kaili Zhao

Abstract: Tracking-by-detection with temporal smoothness has recently attracted increasing attentions in the field of multi-object tracking. Occlusions and clutter are two key problems. To address these problems, this paper proposes a new structure and appearance preserving network flow (SAPNF) with tracking-by-detection, introducing spatial structural configuration and appearance overlapping constraint from frame to frame. One crucial aspect in SAPNF is to consider structure information and appearance smoothness simultaneously which benefits from each other. Unlike previous studies that only learn spatial information or appearance smoothness, a unified min-cost flow with the proposed new structure and appearance induces to track multi-object in crowded and cluttered scenes. Experiments on PETS and TUD benchmarks show that SAPNF performs the comparative results in comparison with alternative methods.