Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers

Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion. Also, an object may leave the field of view and then reappear. In order to track and reacquire an unknown object with limited labeling data, we propose to learn these changes online and build a model that describes all seen appearance while tracking. To address this semi-supervised learning problem, we propose a cotraining based approach to continuously label incoming data and online update a hybrid discriminative generative model. The generative model uses a number of low dimension linear subspaces to describe the appearance of the object. In order to reacquire an object, the generative model encodes all the appearance variations that have been seen. A discriminative classifier is implemented as an online support vector machine, which is trained to focus on recent appearance variations. The online co-training of this hybrid approach account...

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Gérard G. Medioni, Qian Yu, Thang Ba Dinh
• Keywords: Appearance Changes, Computer Vision, Discriminative Classifier, Discriminative Generative Model, ECCV 2008, Hybrid Approach Accounts, Unknown Object