Object Tracking based on Features and Structures

In recent years, we have been studying the potential ofgraph-based methods and representations in thefield of videoobject tracking [1], [2]. Our aim is to track rigid (e.g. man-made objects) and articulated objects (e.g. humans) throughchallenging situations like distractors and occlusions. Further-more, the output should go beyond a single trajectory of thecenter of mass of the object. Especially for articulated objects,we are interested in the local motion of the parts of the object(e.g. limbs of a human body). To achieve this aim, we proposeto represent and to track target objects by a combination ofappearance and structure.