论文标题
准确的锚自由跟踪
Accurate Anchor Free Tracking
论文作者
论文摘要
视觉对象跟踪是计算机视觉的重要应用。最近，基于暹罗的跟踪器取得了良好的准确性。但是，大多数基于暹罗的跟踪器都不有效，因为它们详尽地搜索了潜在的对象位置以定义锚点，然后对每个锚进行分类（即一个边界框）。本文开发了第一个锚自由暹罗网络（AFSN）。具体而言，目标对象由边界框中心定义，跟踪偏移和对象大小。这三个都通过暹罗网络进行了回归，没有其他分类或区域建议，并且每帧执行一次。我们还调整了暹罗网络的步伐和接受场，并进一步进行消融实验，以定量说明我们的AFSN的有效性。我们使用五个最常用的基准测试评估AFSN，并与最佳的基于锚的跟踪器进行比较，并使用每个基准测试的源代码。 AFSN的速度比这些最佳基于锚的跟踪器快3-425倍。 AFSN is also 5.97% to 12.4% more accurate in terms of all metrics for benchmark sets OTB2015, VOT2015, VOT2016, VOT2018 and TrackingNet, except that SiamRPN++ is 4% better than AFSN in terms of Expected Average Overlap (EAO) on VOT2018 (but SiamRPN++ is 3.9 times slower).
Visual object tracking is an important application of computer vision. Recently, Siamese based trackers have achieved good accuracy. However, most of Siamese based trackers are not efficient, as they exhaustively search potential object locations to define anchors and then classify each anchor (i.e., a bounding box). This paper develops the first Anchor Free Siamese Network (AFSN). Specifically, a target object is defined by a bounding box center, tracking offset, and object size. All three are regressed by Siamese network with no additional classification or regional proposal, and performed once for each frame. We also tune the stride and receptive field for Siamese network, and further perform ablation experiments to quantitatively illustrate the effectiveness of our AFSN. We evaluate AFSN using five most commonly used benchmarks and compare to the best anchor-based trackers with source codes available for each benchmark. AFSN is 3-425 times faster than these best anchor based trackers. AFSN is also 5.97% to 12.4% more accurate in terms of all metrics for benchmark sets OTB2015, VOT2015, VOT2016, VOT2018 and TrackingNet, except that SiamRPN++ is 4% better than AFSN in terms of Expected Average Overlap (EAO) on VOT2018 (but SiamRPN++ is 3.9 times slower).
