Complementary Learners for Visual Tracking

At present, Discriminative Correlation Filter(DCF) based trackers and Deep Learning based trackers are the main methods to achieve visual tracking. Although they have achieved promising performance in many cases, there are still some inherent flaws that they can't overcome. Neither of the two main tracking algorithms can achieve satisfactory tracking performance, and considering that they can complement each other to some extent. In this paper, we focus on combining them together for a better tracking. To this end, we select several Correlation Filter and Deep Learning based tracking methods, then modify them appropriately and take different combinations to get a comprehensive result. To meet the real-time requirements, in the DCF branch, we mainly use hand-crafted features rather than deep features. Finally, we propose a new adaptive fusion approach to improve the tracking robustness and accuracy. Comprehensive experiments are performed on several benchmark datasets, using the evaluation criteria which have been proposed by the corresponding benchmarks. In order to fully understand the role of each branch and the effect of fusion strategy, our approach is compared with corresponding individual branches meanwhile the combination of our branches is compared with different fusion strategies. Finally, our approach is compared with state-of-the-art trackers, and the results show that our method has good accuracy and robustness when compared with other methods.