Robust vision tracking by online random ferns and template library

• We propose a robust tracking algorithm based on random ferns and template library.
• Random Gaussian difference is adopted to generate binary features.
• Semi-naive Bayes based random ferns are used to establish discriminative model.
• Co-training of discriminative model and template library improves the accuracy.
• Experiments show a good performance of our tracker on challenging sequences.

In this paper, we proposed a robust tracking algorithm with an appearance model based on random ferns and template library. We adopt random Gaussian difference to generate binary features which depend on two randomly selected points and their corresponding Gaussian blur kernels. Semi-naive Bayes based random ferns are adopted as the discriminative model, and a template library including both positive templates and negative templates is used as generative model, the co-training of both discriminative and generative models gives our tracker the ability to separate foreground and background samples accurately. Besides, we also come up with a fragment based method which combines global ferns and local ferns to handle the occlusion problem. Experimental results demonstrated that the proposed algorithm performs well in terms of accuracy and robustness.