Two stages for visual object tracking
This work addresses the problem of improving tracking accuracy for computer vision applications, representing an incremental advancement by integrating segmentation into Siamese-based trackers.
The paper tackles visual object tracking by proposing a two-stage tracker combining detection and segmentation, achieving state-of-the-art results with EAO scores of 52.6% on VOT2016, 51.3% on VOT2018, and 39.0% on VOT2019 datasets.
Siamese-based trackers have achived promising performance on visual object tracking tasks. Most existing Siamese-based trackers contain two separate branches for tracking, including classification branch and bounding box regression branch. In addition, image segmentation provides an alternative way to obetain the more accurate target region. In this paper, we propose a novel tracker with two-stages: detection and segmentation. The detection stage is capable of locating the target by Siamese networks. Then more accurate tracking results are obtained by segmentation module given the coarse state estimation in the first stage. We conduct experiments on four benchmarks. Our approach achieves state-of-the-art results, with the EAO of 52.6$\%$ on VOT2016, 51.3$\%$ on VOT2018, and 39.0$\%$ on VOT2019 datasets, respectively.