Real-time visual tracking by deep reinforced decision making
This addresses the challenge of unpredictable appearance changes in visual tracking for applications like surveillance or robotics, though it is incremental as it builds on existing confidence map-based methods.
The paper tackles the problem of tracker drift in visual tracking by introducing a real-time algorithm that uses deep reinforcement learning to select appropriate templates, achieving a speed of 43 fps and effective template decisions.
One of the major challenges of model-free visual tracking problem has been the difficulty originating from the unpredictable and drastic changes in the appearance of objects we target to track. Existing methods tackle this problem by updating the appearance model on-line in order to adapt to the changes in the appearance. Despite the success of these methods however, inaccurate and erroneous updates of the appearance model result in a tracker drift. In this paper, we introduce a novel real-time visual tracking algorithm based on a template selection strategy constructed by deep reinforcement learning methods. The tracking algorithm utilizes this strategy to choose the appropriate template for tracking a given frame. The template selection strategy is self-learned by utilizing a simple policy gradient method on numerous training episodes randomly generated from a tracking benchmark dataset. Our proposed reinforcement learning framework is generally applicable to other confidence map based tracking algorithms. The experiment shows that our tracking algorithm runs in real-time speed of 43 fps and the proposed policy network effectively decides the appropriate template for successful visual tracking.