Abstract

Ob ject tracking is a reoccurring problem in computer vision. Tracking-by-detection approaches, in particular Struck [20], have shown to be competitive in recent evaluations. However, such approaches fail in the presence of long-term occlusions as well as severe viewpoint changes of the ob ject. In this paper we propose a principled way to combine occlusion and motion reasoning with a tracking-by-detection approach. Occlusion and motion reasoning is based on state-of-the-art long-term tra jectories which are labeled as ob ject or background tracks with an energy-based formulation. The overlap between labeled tracks and de- tected regions allows to identify occlusions. The motion changes of the ob ject between consecutive frames can be estimated robustly from the geometric relation between ob ject tra jectories. If this geometric change is significant, an additional detector is trained. Experimental results show that our tracker obtains state-of-the-art results and handles occlusion and viewpoints changes better than competing tracking methods.