Scholarlink

<p>Data association is a knotty problem for 2D Multiple Object Tracking due to the object occlusion. However, in 3D space, data association is not so hard. Only with a 3D Kalman Filter, the online object tracker can associate the detections from LiDAR. In this paper, we rethink the data association in 2D MOT and utilize the 3D object representation to separate each object in the feature space. Unlike the existing depth-based MOT methods, the 3D object representation can be jointly learned with the object association module. Besides, the object’s 3D representation is learned from the video and supervised by the 2D tracking labels without additional manual annotations from LiDAR or pretrained depth estimator. With 3D object representation learning from Pseudo 3D (P3D) object labels in monocular videos, we propose a new 2D MOT paradigm, called P3DTrack. Extensive experiments show the effectiveness of our method. We achieve state-of-the-art performance on the ego-centric datasets, KITTI and Waymo Open Dataset (WOD). Code will be released at <a href="https://github.com/jiaweihe1996/p3dtrack">https://github.com/jiaweihe1996/p3dtrack</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Learning Pseudo 3D Representation for Ego-centric 2D Multiple Object Tracking

  • 期刊论文

  • 发表日期：

    2026年6月20日

查看全文
  • Jiawei He,
  • Lue Fan,
  • Zhaoxiang Zhang

摘要

Data association is a knotty problem for 2D Multiple Object Tracking due to the object occlusion. However, in 3D space, data association is not so hard. Only with a 3D Kalman Filter, the online object tracker can associate the detections from LiDAR. In this paper, we rethink the data association in 2D MOT and utilize the 3D object representation to separate each object in the feature space. Unlike the existing depth-based MOT methods, the 3D object representation can be jointly learned with the object association module. Besides, the object’s 3D representation is learned from the video and supervised by the 2D tracking labels without additional manual annotations from LiDAR or pretrained depth estimator. With 3D object representation learning from Pseudo 3D (P3D) object labels in monocular videos, we propose a new 2D MOT paradigm, called P3DTrack. Extensive experiments show the effectiveness of our method. We achieve state-of-the-art performance on the ego-centric datasets, KITTI and Waymo Open Dataset (WOD). Code will be released at https://github.com/jiaweihe1996/p3dtrack.