SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking

Abstract

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.

to appear in CVPR'19

References in corpus (6)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
• Modeling and Propagating CNNs in a Tree Structure for Visual Tracking
• Transferring Rich Feature Hierarchies for Robust Visual Tracking
• Learning regression and verification networks for long-term visual tracking
• LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking

Cited by in corpus (5)

• Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
• SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking
• TRAT: Tracking by Attention Using Spatio-Temporal Features
• Benchmarking Deep Trackers on Aerial Videos
• Saliency-Associated Object Tracking