Online Learning a High-Quality Dictionary and Classifier Jointly for Multitask Object Tracking

Abstract

This article formulates object tracking in a particle filter framework as a binary classification problem. The method effectively exploits a priori information from training data to learn online a compact and discriminative dictionary. The method incorporates the class label information into the dictionary learning process as the classification error term and idea coding regularization term, respectively. Combined with the traditional reconstruction error, a total objective function for dictionary learning is constructed. By minimizing the total object function, the approach jointly obtains a high-quality dictionary and optimal linear classifier. Combined with multitask sparse coding, the best candidate is selected by jointly evaluating the reconstructive error and classification error. As the tracking continues, the proposed algorithm alternates between multitask sparse coding and dictionary updating. Experimental evaluations on challenging video sequences show that the proposed algorithm performs favorably against state-of-the-art methods in terms of effectiveness, accuracy, and robustness.