Visual tracking via orthogonal sparse coding

In this paper, we incorporate sparse coding and orthogonal dictionary learning into a unified framework, named orthogonal sparse coding (OSC), for robust visual tracking. Different from previous tracking methods, which often use redundant dictionaries, OSC enforces an orthogonality constraint in the dictionary learning step to adaptively capture the structures of the video sequences. Moreover, a ℓ₀ norm regularizer is introduced in OSC formulation to address the severe noise problems, illumination changes, and occlusions in real world videos. As a nontrivial byproduct, we develop an efficient numerical solver to address the optimization issues of our OSC model. Experimental results on various challenging video sequences show that the proposed method achieves better performance both on accuracy and speed compared to proposed state-of-the-art methods.