Multiple-object tracking based on monocular camera and 3-D lidar fusion for autonomous vehicles

Hao Chen; Chunyue Xue; Shoubin Liu; Yuxiang Sun; Yongquan Chen

doi:10.1109/ROBIO49542.2019.8961438

Multiple-object tracking based on monocular camera and 3-D lidar fusion for autonomous vehicles

Hao Chen
, Chunyue Xue
, Shoubin Liu
, Yuxiang Sun
, Yongquan Chen^*

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

7 Citations (Scopus)

Abstract

This article describes a multi-object tracking method through sensor fusion with a monocular camera and a 3-D Lidar for autonomous vehicles. Specifically, several pairwise costs from information, such as locations, movements, and poses of 3-D cues, are designed for tracking. These costs can complement each other to reduce matching errors during the tracking process. Moreover, they are efficient to be on-line computed with embedded equipment. We feed the pairwise costs to the data-association framework, which is based on the Hungarian algorithm, and then do the back-end fusion for the tracking results. The experimental results on our autonomous sightseeing car demonstrate that our tracking method could achieve accurate and robust results in real-world traffic scenarios. © 2019 IEEE.

Original language	English
Title of host publication	IEEE International Conference on Robotics and Biomimetics, ROBIO 2019
Publisher	IEEE
Pages	456-460
ISBN (Electronic)	9781728163215, 978-1-7281-6320-8
ISBN (Print)	978-1-7281-6322-2
DOIs	https://doi.org/10.1109/ROBIO49542.2019.8961438
Publication status	Published - Dec 2019
Externally published	Yes
Event	2019 IEEE International Conference on Robotics and Biomimetics (ROBIO 2019) - Dali, China Duration: 6 Dec 2019 → 8 Dec 2019

Publication series

Name	IEEE International Conference on Robotics and Biomimetics, ROBIO

Conference

Conference	2019 IEEE International Conference on Robotics and Biomimetics (ROBIO 2019)
Abbreviated title	IEEE ROBIO 2019
Place	China
City	Dali
Period	6/12/19 → 8/12/19

Funding

This paper is partially supported by Shenzhen Fundamental Research grant (JCYJ20180508162406177) and the National Natural Science Foundation of China (U1613216) from The Chinese University of Hong Kong, Shenzhen. This paper is also partially supported by funding from Shenzhen Institute of Artificial Intelligence and Robotics for Society.

Access Output

10.1109/ROBIO49542.2019.8961438

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{d5b60fb3f55840b5ab04f45102a2ad1e,

title = "Multiple-object tracking based on monocular camera and 3-D lidar fusion for autonomous vehicles",

abstract = "This article describes a multi-object tracking method through sensor fusion with a monocular camera and a 3-D Lidar for autonomous vehicles. Specifically, several pairwise costs from information, such as locations, movements, and poses of 3-D cues, are designed for tracking. These costs can complement each other to reduce matching errors during the tracking process. Moreover, they are efficient to be on-line computed with embedded equipment. We feed the pairwise costs to the data-association framework, which is based on the Hungarian algorithm, and then do the back-end fusion for the tracking results. The experimental results on our autonomous sightseeing car demonstrate that our tracking method could achieve accurate and robust results in real-world traffic scenarios. {\textcopyright} 2019 IEEE.",

author = "Hao Chen and Chunyue Xue and Shoubin Liu and Yuxiang Sun and Yongquan Chen",

year = "2019",

month = dec,

doi = "10.1109/ROBIO49542.2019.8961438",

language = "English",

isbn = "978-1-7281-6322-2",

series = "IEEE International Conference on Robotics and Biomimetics, ROBIO",

publisher = "IEEE",

pages = "456--460",

booktitle = "IEEE International Conference on Robotics and Biomimetics, ROBIO 2019",

address = "United States",

note = "2019 IEEE International Conference on Robotics and Biomimetics (ROBIO 2019), IEEE ROBIO 2019 ; Conference date: 06-12-2019 Through 08-12-2019",

}

Chen, H, Xue, C, Liu, S, Sun, Y & Chen, Y 2019, Multiple-object tracking based on monocular camera and 3-D lidar fusion for autonomous vehicles. in IEEE International Conference on Robotics and Biomimetics, ROBIO 2019. IEEE International Conference on Robotics and Biomimetics, ROBIO, IEEE, pp. 456-460, 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO 2019), Dali, China, 6/12/19. https://doi.org/10.1109/ROBIO49542.2019.8961438

Multiple-object tracking based on monocular camera and 3-D lidar fusion for autonomous vehicles. / Chen, Hao; Xue, Chunyue; Liu, Shoubin et al.
IEEE International Conference on Robotics and Biomimetics, ROBIO 2019. IEEE, 2019. p. 456-460 (IEEE International Conference on Robotics and Biomimetics, ROBIO).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Multiple-object tracking based on monocular camera and 3-D lidar fusion for autonomous vehicles

AU - Chen, Hao

AU - Xue, Chunyue

AU - Liu, Shoubin

AU - Sun, Yuxiang

AU - Chen, Yongquan

PY - 2019/12

Y1 - 2019/12

N2 - This article describes a multi-object tracking method through sensor fusion with a monocular camera and a 3-D Lidar for autonomous vehicles. Specifically, several pairwise costs from information, such as locations, movements, and poses of 3-D cues, are designed for tracking. These costs can complement each other to reduce matching errors during the tracking process. Moreover, they are efficient to be on-line computed with embedded equipment. We feed the pairwise costs to the data-association framework, which is based on the Hungarian algorithm, and then do the back-end fusion for the tracking results. The experimental results on our autonomous sightseeing car demonstrate that our tracking method could achieve accurate and robust results in real-world traffic scenarios. © 2019 IEEE.

AB - This article describes a multi-object tracking method through sensor fusion with a monocular camera and a 3-D Lidar for autonomous vehicles. Specifically, several pairwise costs from information, such as locations, movements, and poses of 3-D cues, are designed for tracking. These costs can complement each other to reduce matching errors during the tracking process. Moreover, they are efficient to be on-line computed with embedded equipment. We feed the pairwise costs to the data-association framework, which is based on the Hungarian algorithm, and then do the back-end fusion for the tracking results. The experimental results on our autonomous sightseeing car demonstrate that our tracking method could achieve accurate and robust results in real-world traffic scenarios. © 2019 IEEE.

UR - https://www.scopus.com/pages/publications/85079031427

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85079031427&origin=recordpage

U2 - 10.1109/ROBIO49542.2019.8961438

DO - 10.1109/ROBIO49542.2019.8961438

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-1-7281-6322-2

T3 - IEEE International Conference on Robotics and Biomimetics, ROBIO

SP - 456

EP - 460

BT - IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

PB - IEEE

T2 - 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO 2019)

Y2 - 6 December 2019 through 8 December 2019

ER -

Multiple-object tracking based on monocular camera and 3-D lidar fusion for autonomous vehicles

Abstract

Publication series

Conference

Funding

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this