Dynamic objectness for adaptive tracking

Abstract. A fundamental problem of object tracking is to adapt to un-seen views of the object while not getting distracted by other objects. We introduce Dynamic Objectness in a discriminative tracking frame-work to sporadically re-discover the tracked object based on motion. In doing so, drifting is effectively limited since tracking becomes more aware of objects as independently moving entities in the scene. The approach not only follows the object, but also the background to not easily adapt to other distracting objects. Finally, an appearance model of the ob-ject is incrementally built for an eventual re-detection after a partial or full occlusion. We evaluated it on several well-known tracking sequences and demonstrate results with superior accuracy, especially in difficult se-quences with changing aspect ratios, varying scale, partial occlusion and non-rigid objects.