Abstract

In object tracking, change of object aspect is a cause of failure due to significant changes of object appearances. The paper proposes an approach to this problem without a priori learning object views. The object identification relies on a discriminative model using both object and background appearances. The background is represented as a set of texture patterns. The tracking algorithm then maintains a set of discriminant functions each recognizing a pattern in the object region against the background patterns that are currently relevant. Object matching is then performed efficiently by maximization of the sum of the discriminant functions over all object patterns. As a result, the tracker searches for the region that matches the target object and it also avoids background patterns seen before. The results of the experiment show that the proposed tracker is robust to even severe aspect changes when unseen views of the object come into view.