DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion
复制标题
DOI：
10.1109/cvpr52688.2022.02032
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Pei Sun;Jinkun Cao;Yi Jiang;Zehuan Yuan;S. Bai;Kris Kitani;P. Luo
中科院分区：
文献类型：
--
作者：
Pei Sun;Jinkun Cao;Yi Jiang;Zehuan Yuan;S. Bai;Kris Kitani;P. Luo
用于多目标跟踪(MOT)的典型流水线是使用检测器进行目标定位，然后使用重新识别(Re-ID)来进行目标关联。这条管道的部分原因是对象检测和Re-ID方面的最新进展，部分原因是现有跟踪数据集中的偏差，其中大多数对象往往具有可识别的外观，并且Re-ID模型足以用于建立关联。针对这种偏见，我们要再次强调，当物体外观不够有辨别力时，多目标跟踪的方法也应该起作用。为此，我们提出了一个用于多人跟踪的大规模数据集，其中的人类具有相似的外表、多样的运动和极端的清晰度。由于数据集包含的大部分是集体舞视频，我们将其命名为DanceTrack。我们期待DanceTrack提供一个更好的平台来开发更多的MOT算法，减少对视觉辨别的依赖，更多地依赖于运动分析。我们在我们的数据集上对几个最先进的跟踪器进行了基准测试，并观察到与现有基准相比，DanceTrack的性能显著下降。数据集、项目代码和竞赛在以下网站发布：https://github.com/DanceTrack.
A typical pipeline for multi-object tracking (MOT) is to use a detector for object localization, and following re-identification (re-ID)for object association. This pipeline is partially motivated by recent progress in both object detection and re- ID, and partially motivated by biases in existing tracking datasets, where most objects tend to have distin-guishing appearance and re-ID models are sufficient for es-tablishing associations. In response to such bias, we would like to re-emphasize that methods for multi-object tracking should also work when object appearance is not sufficiently discriminative. To this end, we propose a large-scale dataset for multi-human tracking, where humans have sim-ilar appearance, diverse motion and extreme articulation. As the dataset contains mostly group dancing videos, we name it “DanceTrack”. We expect DanceTrack to provide a better platform to develop more MOT algorithms that rely less on visual discrimination and depend more on motion analysis. We benchmark several state-of-the-art trackers on our dataset and observe a significant performance drop on DanceTrack when compared against existing benchmarks. The dataset, project code and competition is released at: https://github.com/DanceTrack.