Embedding holistic appearance information in part-based adaptive appearance model for robust visual tracking

Part-based adaptive appearance model has been extensively used in increasingly popular discriminative trackers. The main problem of these methods is the stability plasticity dilemma. Embedding holistic appearance information in the part-based appearance model which is learned online to alleviate this problem is proposed. Specifically, the object is represented by sparse multi-scale Haar-like features and the appearance model is constructed with a naive Bayes classifier. Unlike the conventional methods, the classifier is trained by positive and negative samples that are weighted according to their similarity with the holistic appearance model, which is kept constant during the updating procedure. The constant holistic appearance information providing some constraints when updating the part-based appearance model makes the tracker more stable. The online updating procedure of the part-based appearance model makes the tracker adaptive enough to appearance changes. Experimental results demonstrate the superior performance of the proposed method compared with several state-of-art algorithms.