You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xiyang, Fu, Chunyun, He, Jiawei, Huang, Mingguang, Meng, Ting, Zhang, Siyu, Zhou, Hangning, Xu, Ziyao, Zhang, Chi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917619559301120
author Wang, Xiyang
Fu, Chunyun
He, Jiawei
Huang, Mingguang
Meng, Ting
Zhang, Siyu
Zhou, Hangning
Xu, Ziyao
Zhang, Chi
author_facet Wang, Xiyang
Fu, Chunyun
He, Jiawei
Huang, Mingguang
Meng, Ting
Zhang, Siyu
Zhou, Hangning
Xu, Ziyao
Zhang, Chi
contents In the classical tracking-by-detection (TBD) paradigm, detection and tracking are separately and sequentially conducted, and data association must be properly performed to achieve satisfactory tracking performance. In this paper, a new end-to-end multi-object tracking framework is proposed, which integrates object detection and multi-object tracking into a single model. The proposed tracking framework eliminates the complex data association process in the classical TBD paradigm, and requires no additional training. Secondly, the regression confidence of historical trajectories is investigated, and the possible states of a trajectory (weak object or strong object) in the current frame are predicted. Then, a confidence fusion module is designed to guide non-maximum suppression for trajectories and detections to achieve ordered and robust tracking. Thirdly, by integrating historical trajectory features, the regression performance of the detector is enhanced, which better reflects the occlusion and disappearance patterns of objects in real world. Lastly, extensive experiments are conducted on the commonly used KITTI and Waymo datasets. The results show that the proposed framework can achieve robust tracking by using only a 2D detector and a 3D detector, and it is proven more accurate than many of the state-of-the-art TBD-based multi-modal tracking methods. The source codes of the proposed method are available at https://github.com/wangxiyang2022/YONTD-MOT.
format Preprint
id arxiv_https___arxiv_org_abs_2304_08709
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking
Wang, Xiyang
Fu, Chunyun
He, Jiawei
Huang, Mingguang
Meng, Ting
Zhang, Siyu
Zhou, Hangning
Xu, Ziyao
Zhang, Chi
Computer Vision and Pattern Recognition
In the classical tracking-by-detection (TBD) paradigm, detection and tracking are separately and sequentially conducted, and data association must be properly performed to achieve satisfactory tracking performance. In this paper, a new end-to-end multi-object tracking framework is proposed, which integrates object detection and multi-object tracking into a single model. The proposed tracking framework eliminates the complex data association process in the classical TBD paradigm, and requires no additional training. Secondly, the regression confidence of historical trajectories is investigated, and the possible states of a trajectory (weak object or strong object) in the current frame are predicted. Then, a confidence fusion module is designed to guide non-maximum suppression for trajectories and detections to achieve ordered and robust tracking. Thirdly, by integrating historical trajectory features, the regression performance of the detector is enhanced, which better reflects the occlusion and disappearance patterns of objects in real world. Lastly, extensive experiments are conducted on the commonly used KITTI and Waymo datasets. The results show that the proposed framework can achieve robust tracking by using only a 2D detector and a 3D detector, and it is proven more accurate than many of the state-of-the-art TBD-based multi-modal tracking methods. The source codes of the proposed method are available at https://github.com/wangxiyang2022/YONTD-MOT.
title You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.08709