Towards a Better Match in Siamese Network Based Visual Object Tracker
This work addresses visual object tracking for real-time applications, offering incremental improvements to existing Siamese-based methods.
The paper tackles limitations in Siamese network trackers, specifically handling large object rotation and background distractions, by introducing angle estimation and spatial masking, achieving a state-of-the-art EAO of 0.335 on VOT2017 while maintaining real-time capability.
Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance. Despite the great success, this tracking framework still suffers from several limitations. First, it cannot properly handle large object rotation. Second, tracking gets easily distracted when the background contains salient objects. In this paper, we propose two simple yet effective mechanisms, namely angle estimation and spatial masking, to address these issues. The objective is to extract more representative features so that a better match can be obtained between the same object from different frames. The resulting tracker, named Siam-BM, not only significantly improves the tracking performance, but more importantly maintains the realtime capability. Evaluations on the VOT2017 dataset show that Siam-BM achieves an EAO of 0.335, which makes it the best-performing realtime tracker to date.