Maximum Entropy Reinforced Single Object Visual Tracking

Single object visual tracking is a fundamental problem in computer vision and has many applications. Given only the location of the target of interest in the first video frame, a visual tracking algorithm must track the target until the end of the video while having to face challenging factors such as illumination change and scale variation. In this paper, we formulate this tracking problem in a framework of maximum entropy reinforcement learning where the agent is our visual tracker and the goal is to learn a tracking policy that maximises both the expected reward and its entropy so as to achieve a balance between exploitation and exploration. The aim of our tracking framework is to improve the tracking accuracy while giving the tracking agent the ability to avoid getting stuck on a nontarget object. Extensive experiments have been performed on a range of benchmarks where our method achieves state-of-the-art performance. Furthermore, we demonstrate that, in contrast to other visual trackers based on deep reinforcement learning, our method can run in real-time while maintaining high tracking accuracy.