A Lightweight and Detector-Free 3D Single Object Tracker on Point Clouds

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

21 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)5543-5554
Journal / PublicationIEEE Transactions on Intelligent Transportation Systems
Volume24
Issue number5
Online published22 Feb 2023
Publication statusPublished - May 2023

Link(s)

Abstract

Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off the-shelf 3D detector is commonly employed for the tracking. However, it is non-trivial to perform accurate target-specific detection since the point cloud of objects in raw LiDAR scans is usually sparse and incomplete. In this paper, we address this issue by explicitly leveraging temporal motion cues and propose DMT, a Detector-free Motion-prediction-based 3D Tracking network that completely removes the usage of complicated 3D detectors and is lighter, faster, and more accurate than previous trackers. Specifically, the motion prediction module is first introduced to estimate a potential target center of the current frame in a point-cloud-free manner. Then, an explicit voting module is proposed to directly regress the 3D box from the estimated target center. Extensive experiments on KITTI and NuScenes datasets demonstrate that our DMT can still achieve better performance (∼10% improvement over the NuScenes dataset) and a faster tracking speed (i.e., 72 FPS) than state-of-the-art approaches without applying any complicated 3D detectors. Our code is released at https://github.com/jimmy-dq/DMT. © 2023 IEEE.

Research Area(s)

  • Three-dimensional displays, Target tracking, Point cloud compression, Proposals, Object tracking, Detectors, Search problems, Point clouds, detector-free, explicit voting, 3D single object tracking

Download Statistics

No data available