当前位置: X-MOL 学术arXiv.cs.CV › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Spatio-Temporal Matching for Siamese Visual Tracking
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2021-05-06 , DOI: arxiv-2105.02408
Jinpu Zhang, Yuehuan Wang

Similarity matching is a core operation in Siamese trackers. Most Siamese trackers carry out similarity learning via cross correlation that originates from the image matching field. However, unlike 2-D image matching, the matching network in object tracking requires 4-D information (height, width, channel and time). Cross correlation neglects the information from channel and time dimensions, and thus produces ambiguous matching. This paper proposes a spatio-temporal matching process to thoroughly explore the capability of 4-D matching in space (height, width and channel) and time. In spatial matching, we introduce a space-variant channel-guided correlation (SVC-Corr) to recalibrate channel-wise feature responses for each spatial location, which can guide the generation of the target-aware matching features. In temporal matching, we investigate the time-domain context relations of the target and the background and develop an aberrance repressed module (ARM). By restricting the abrupt alteration in the interframe response maps, our ARM can clearly suppress aberrances and thus enables more robust and accurate object tracking. Furthermore, a novel anchor-free tracking framework is presented to accommodate these innovations. Experiments on challenging benchmarks including OTB100, VOT2018, VOT2020, GOT-10k, and LaSOT demonstrate the state-of-the-art performance of the proposed method.

中文翻译:

时空匹配用于暹罗视觉跟踪

相似性匹配是暹罗跟踪器的核心操作。大多数暹罗跟踪器通过源自图像匹配领域的互相关来进行相似性学习。但是,与2D图像匹配不同,对象跟踪中的匹配网络需要4D信息(高度,宽度,通道和时间)。互相关忽略了来自通道和时间维度的信息,因此产生了模棱两可的匹配。本文提出了一种时空匹配过程,以彻底探索空间(高度,宽度和通道)和时间中4-D匹配的能力。在空间匹配中,我们引入了空间变量通道引导相关性(SVC-Corr),以重新校准每个空间位置的通道方式特征响应,这可以指导目标感知匹配特征的生成。在时间匹配中,我们研究了目标和背景的时域上下文关系,并开发了异常抑制模块(ARM)。通过限制帧间响应图中的突然变化,我们的ARM可以清楚地抑制异常,从而实现更强大和准确的对象跟踪。此外,提出了一种新颖的无锚跟踪框架来适应这些创新。在具有挑战性的基准(包括OTB100,VOT2018,VOT2020,GOT-10k和LaSOT)上进行的实验证明了该方法的最新性能。提出了一种新颖的无锚跟踪框架来适应这些创新。在具有挑战性的基准(包括OTB100,VOT2018,VOT2020,GOT-10k和LaSOT)上进行的实验证明了该方法的最新性能。提出了一种新颖的无锚跟踪框架来适应这些创新。在具有挑战性的基准(包括OTB100,VOT2018,VOT2020,GOT-10k和LaSOT)上进行的实验证明了该方法的最新性能。
更新日期:2021-05-07
down
wechat
bug