前戏
最近出了真的很多很多论文,各种SOTA。比如今天po的多目标跟踪方向的论文,明天应该会po一篇人群密度估计或者目标检测方向的SOTA论文。最新的论文,Amusi就不详细解读了(可能自己也不会)。
因为论文这玩意,还是要自己去品才有滋味。或许过两天,论文的作者团队会解读一番,对照着作者的解答来理解,这才原滋原味。
正文
《Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification》
arXiv:https://arxiv.org/abs/1901.06129
作者团队:商汤&北航&悉尼大学
注:2019年01月21日刚出炉的paper
Abstract: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.
摘要:在本文中,我们提出了一个统一的多目标跟踪(MOT)框架,可以学会充分利用长期和短期线索来处理MOT场景中的复杂情况。此外,为了更好地关联,我们提出了切换器感知分类(SAC),它考虑了潜在的身份切换监视器(切换器)。 具体而言,所提出的框架包括用于捕获短期线索的单个对象跟踪(SOT)子网络,用于提取长期线索的 ReID 子网络以及用于使用提取的特征进行匹配决策的切换器感知分类器。 从主目标和切换器。短期线索有助于发现漏报(FN),而长期线索避免了发生遮挡时的严重错误,并且SAC学会以有效的方式组合多个线索并提高稳健性。该方法在具有挑战性的MOT基准测试中进行评估,并达到 SOTA。
The proposed MOT framework
Siamese-RPN architecture for SOT
创新点
Using SOT Tracker for Short Term Cues
Using ReID Network for Long Term Cues
Switcher-Aware Classifier
SOTA(MOT16 and MOT17)
识别示例