SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
This work addresses the problem of real-time visual object tracking for applications like surveillance and robotics, offering incremental improvements over existing real-time trackers.
The paper tackled the challenge of balancing robustness and discrimination in visual object tracking by proposing SPM-Tracker, which uses a series-parallel matching structure to separate these requirements into two stages, resulting in superior performance with an AUC of 0.687 on OTB-100 and an EAO of 0.434 on VOT-16 while running at 120fps.
The greatest challenge facing visual object tracking is the simultaneous requirements on robustness and discrimination power. In this paper, we propose a SiamFC-based tracker, named SPM-Tracker, to tackle this challenge. The basic idea is to address the two requirements in two separate matching stages. Robustness is strengthened in the coarse matching (CM) stage through generalized training while discrimination power is enhanced in the fine matching (FM) stage through a distance learning network. The two stages are connected in series as the input proposals of the FM stage are generated by the CM stage. They are also connected in parallel as the matching scores and box location refinements are fused to generate the final results. This innovative series-parallel structure takes advantage of both stages and results in superior performance. The proposed SPM-Tracker, running at 120fps on GPU, achieves an AUC of 0.687 on OTB-100 and an EAO of 0.434 on VOT-16, exceeding other real-time trackers by a notable margin.