Globally Optimal Object Tracking with Fully Convolutional Networks
This work addresses the problem of robust object tracking for computer vision applications, but it appears incremental as it combines existing techniques (FCN and DP) without claiming major breakthroughs.
The paper tackles object tracking in videos by addressing appearance variation and occlusion, proposing a method that combines a Fully Convolutional Network for object probability maps with Dynamic Programming for globally optimal paths, achieving effective tracking of various single objects.
Tracking is one of the most important but still difficult tasks in computer vision and pattern recognition. The main difficulties in the tracking field are appearance variation and occlusion. Most traditional tracking methods set the parameters or templates to track target objects in advance and should be modified accordingly. Thus, we propose a new and robust tracking method using a Fully Convolutional Network (FCN) to obtain an object probability map and Dynamic Programming (DP) to seek the globally optimal path through all frames of video. Our proposed method solves the object appearance variation problem with the use of a FCN and deals with occlusion by DP. We show that our method is effective in tracking various single objects through video frames.