DSRRTracker: Dynamic Search Region Refinement for Attention-based Siamese Multi-Object Tracking
This work addresses multi-object tracking for applications like surveillance and autonomous driving, offering an incremental improvement in efficiency and accuracy.
The paper tackled the suboptimal performance and speed limitations in multi-object tracking by proposing an end-to-end method with a dynamic search region refinement module and attention-based tracking head, achieving state-of-the-art results on MOT17 and MOT20 datasets.
Many multi-object tracking (MOT) methods follow the framework of "tracking by detection", which associates the target objects-of-interest based on the detection results. However, due to the separate models for detection and association, the tracking results are not optimal.Moreover, the speed is limited by some cumbersome association methods to achieve high tracking performance. In this work, we propose an end-to-end MOT method, with a Gaussian filter-inspired dynamic search region refinement module to dynamically filter and refine the search region by considering both the template information from the past frames and the detection results from the current frame with little computational burden, and a lightweight attention-based tracking head to achieve the effective fine-grained instance association. Extensive experiments and ablation study on MOT17 and MOT20 datasets demonstrate that our method can achieve the state-of-the-art performance with reasonable speed.