arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.06129cs.CV
收藏

多线索多目标跟踪与切换感知分类

Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification

Sensetime Group Limited(商汤集团有限公司);Beihang University(北京航空航天大学);The University of Sydney(悉尼大学)

Weitao Feng, Zhihao Hu, Wei Wu, Junjie Yan, Wanli Ouyang

摘要:

在本文中,我们提出了一个统一的多目标跟踪(MOT)框架学习,充分利用长期和短期的线索处理复杂的情况下,在MOT场景。此外,为了更好的关联,我们提出了切换感知分类(SAC),它考虑到潜在的身份切换的原因(切换)。具体而言,所提出的框架包括一个单一的对象跟踪(SOT)子网捕捉短期线索,一个重新识别(ReID)子网提取长期线索和切换感知分类器进行匹配决策使用提取的功能,从主要目标和切换。短期线索有助于发现假阴性,而长期线索避免了发生遮挡时的严重错误,SAC学会以有效的方式组合多个线索并提高鲁棒性。该方法是具有挑战性的MOT基准进行评估,并取得了国家的最先进的结果。

英文摘要:

In this paper, we propose a unified Multi-Object Tracking (MOT) framework learning to make full use of long term and short term cues for handling complex cases in MOT scenes. Besides, for better association, we propose switcher-aware classification (SAC), which takes the potential identity-switch causer (switcher) into consideration. Specifically, the proposed framework includes a Single Object Tracking (SOT) sub-net to capture short term cues, a re-identification (ReID) sub-net to extract long term cues and a switcher-aware classifier to make matching decisions using extracted features from the main target and the switcher. Short term cues help to find false negatives, while long term cues avoid critical mistakes when occlusion happens, and the SAC learns to combine multiple cues in an effective way and improves robustness. The method is evaluated on the challenging MOT benchmarks and achieves the state-of-the-art results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑