arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00380cs.CV
收藏

跨任务协同的在线多目标跟踪

Online Multiple Object Tracking with Cross-Task Synergy

The University of Sydney(悉尼大学);ShanghaiTech University(上海科技大学);National University of Singapore(新加坡国立大学);Stevens Institute of Technology(史蒂文斯理工学院)

Song Guo, Jingya Wang, Xinchao Wang, Dacheng Tao

摘要:

现代在线多目标跟踪方法通常从两个方面来提高跟踪性能。一种是基于来自先前帧的跟踪信息来预测传入帧中的新位置,另一种是通过生成更具区分性的身份嵌入来增强数据关联。有些作品将这两个方向结合在一个框架内,但将它们作为两个单独的任务处理,从而获得很少的互利。在本文中,我们提出了一种新的统一模型之间的协同位置预测和嵌入关联。这两个任务是由时间意识的目标注意和分心物注意,以及身份意识的记忆聚合模型。具体而言,注意力模块可以使预测更多地关注目标,而不是干扰物,因此可以相应地提取更可靠的嵌入以进行关联。另一方面,这种可靠的嵌入可以通过记忆聚合来提高身份意识,从而加强注意力模块并抑制漂移。通过这种方式,实现了位置预测和嵌入关联之间的协同作用,这导致了对遮挡的强鲁棒性。大量的实验表明,我们提出的模型在MOTChallenge基准测试的各种现有方法的优越性。我们的代码和模型可在https://github.com/songguocode/TADAM上公开获取。

英文摘要:

Modern online multiple object tracking (MOT) methods usually focus on two directions to improve tracking performance. One is to predict new positions in an incoming frame based on tracking information from previous frames, and the other is to enhance data association by generating more discriminative identity embeddings. Some works combined both directions within one framework but handled them as two individual tasks, thus gaining little mutual benefits. In this paper, we propose a novel unified model with synergy between position prediction and embedding association. The two tasks are linked by temporal-aware target attention and distractor attention, as well as identity-aware memory aggregation model. Specifically, the attention modules can make the prediction focus more on targets and less on distractors, therefore more reliable embeddings can be extracted accordingly for association. On the other hand, such reliable embeddings can boost identity-awareness through memory aggregation, hence strengthen attention modules and suppress drifts. In this way, the synergy between position prediction and embedding association is achieved, which leads to strong robustness to occlusions. Extensive experiments demonstrate the superiority of our proposed model over a wide range of existing methods on MOTChallenge benchmarks. Our code and models are publicly available at https://github.com/songguocode/TADAM.

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。

↑