A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching

Junzhi Zhu; Xiaolong Wang; Fengli Yang; Long Zhao

doi:10.1007/978-981-99-6847-3_52

A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching

Junzhi Zhu
, Xiaolong Wang
, Fengli Yang
, Long Zhao^*

^*此作品的通讯作者

自动化科学与电气工程学院

Beihang University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Visual based single-object tracking is a classical task in computer vision, which uses texture and color to distinguish objects and backgrounds. However, visual based methods are sensitive to illumination change and motion blur. So, we propose a coarse-to-fine visual-lidar fusion algorithm. This algorithm integrates a visual subsystem and a lidar subsystem. We use the visual subsystem to calculate a coarse position of the object, and then we use the lidar subsystem to optimize it to obtain an accurate position. Compared to visual tracking algorithms, our algorithm is more accurate and robust.

源语言	英语
主期刊名	Proceedings of 2023 Chinese Intelligent Systems Conference - Volume I
编辑	Yingmin Jia, Weicun Zhang, Yongling Fu, Jiqiang Wang
出版商	Springer Science and Business Media Deutschland GmbH
页	607-616
页数	10
ISBN（印刷版）	9789819968466
DOI	https://doi.org/10.1007/978-981-99-6847-3_52
出版状态	已出版 - 2023
活动	19th Chinese Intelligent Systems Conference, CISC 2023 - Ningbo, 中国期限: 14 10月 2023 → 15 10月 2023

出版系列

姓名	Lecture Notes in Electrical Engineering
卷	1089 LNEE
ISSN（印刷版）	1876-1100
ISSN（电子版）	1876-1119

会议

会议	19th Chinese Intelligent Systems Conference, CISC 2023
国家/地区	中国
市	Ningbo
时期	14/10/23 → 15/10/23

访问文件

10.1007/978-981-99-6847-3_52

其它文件与链接

链接到 Scopus 的出版物

引用此

Zhu, J., Wang, X., Yang, F., & Zhao, L. (2023). A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching. 在 Y. Jia, W. Zhang, Y. Fu, & J. Wang (编辑), Proceedings of 2023 Chinese Intelligent Systems Conference - Volume I (页码 607-616). (Lecture Notes in Electrical Engineering; 卷 1089 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-6847-3_52

Zhu, Junzhi ; Wang, Xiaolong ; Yang, Fengli 等. / A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching. Proceedings of 2023 Chinese Intelligent Systems Conference - Volume I. 编辑 / Yingmin Jia ; Weicun Zhang ; Yongling Fu ; Jiqiang Wang. Springer Science and Business Media Deutschland GmbH, 2023. 页码 607-616 (Lecture Notes in Electrical Engineering).

@inproceedings{f3ee3d28bcdf4c3787a1f9614ca83612,

title = "A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching",

abstract = "Visual based single-object tracking is a classical task in computer vision, which uses texture and color to distinguish objects and backgrounds. However, visual based methods are sensitive to illumination change and motion blur. So, we propose a coarse-to-fine visual-lidar fusion algorithm. This algorithm integrates a visual subsystem and a lidar subsystem. We use the visual subsystem to calculate a coarse position of the object, and then we use the lidar subsystem to optimize it to obtain an accurate position. Compared to visual tracking algorithms, our algorithm is more accurate and robust.",

keywords = "Coarse-to-fine method, Single-object tracking, Visual-lidar fusion algorithm",

author = "Junzhi Zhu and Xiaolong Wang and Fengli Yang and Long Zhao",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 19th Chinese Intelligent Systems Conference, CISC 2023 ; Conference date: 14-10-2023 Through 15-10-2023",

year = "2023",

doi = "10.1007/978-981-99-6847-3\_52",

language = "英语",

isbn = "9789819968466",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "607--616",

editor = "Yingmin Jia and Weicun Zhang and Yongling Fu and Jiqiang Wang",

booktitle = "Proceedings of 2023 Chinese Intelligent Systems Conference - Volume I",

address = "德国",

}

Zhu, J, Wang, X, Yang, F & Zhao, L 2023, A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching. 在 Y Jia, W Zhang, Y Fu & J Wang (编辑), Proceedings of 2023 Chinese Intelligent Systems Conference - Volume I. Lecture Notes in Electrical Engineering, 卷 1089 LNEE, Springer Science and Business Media Deutschland GmbH, 页码 607-616, 19th Chinese Intelligent Systems Conference, CISC 2023, Ningbo, 中国, 14/10/23. https://doi.org/10.1007/978-981-99-6847-3_52

A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching. / Zhu, Junzhi; Wang, Xiaolong; Yang, Fengli 等.
Proceedings of 2023 Chinese Intelligent Systems Conference - Volume I. 编辑 / Yingmin Jia; Weicun Zhang; Yongling Fu; Jiqiang Wang. Springer Science and Business Media Deutschland GmbH, 2023. 页码 607-616 (Lecture Notes in Electrical Engineering; 卷 1089 LNEE).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching

AU - Zhu, Junzhi

AU - Wang, Xiaolong

AU - Yang, Fengli

AU - Zhao, Long

PY - 2023

Y1 - 2023

N2 - Visual based single-object tracking is a classical task in computer vision, which uses texture and color to distinguish objects and backgrounds. However, visual based methods are sensitive to illumination change and motion blur. So, we propose a coarse-to-fine visual-lidar fusion algorithm. This algorithm integrates a visual subsystem and a lidar subsystem. We use the visual subsystem to calculate a coarse position of the object, and then we use the lidar subsystem to optimize it to obtain an accurate position. Compared to visual tracking algorithms, our algorithm is more accurate and robust.

AB - Visual based single-object tracking is a classical task in computer vision, which uses texture and color to distinguish objects and backgrounds. However, visual based methods are sensitive to illumination change and motion blur. So, we propose a coarse-to-fine visual-lidar fusion algorithm. This algorithm integrates a visual subsystem and a lidar subsystem. We use the visual subsystem to calculate a coarse position of the object, and then we use the lidar subsystem to optimize it to obtain an accurate position. Compared to visual tracking algorithms, our algorithm is more accurate and robust.

KW - Coarse-to-fine method

KW - Single-object tracking

KW - Visual-lidar fusion algorithm

UR - https://www.scopus.com/pages/publications/85174551740

U2 - 10.1007/978-981-99-6847-3_52

DO - 10.1007/978-981-99-6847-3_52

M3 - 会议稿件

AN - SCOPUS:85174551740

SN - 9789819968466

T3 - Lecture Notes in Electrical Engineering

SP - 607

EP - 616

BT - Proceedings of 2023 Chinese Intelligent Systems Conference - Volume I

A2 - Jia, Yingmin

A2 - Zhang, Weicun

A2 - Fu, Yongling

A2 - Wang, Jiqiang

PB - Springer Science and Business Media Deutschland GmbH

T2 - 19th Chinese Intelligent Systems Conference, CISC 2023

Y2 - 14 October 2023 through 15 October 2023

ER -

Zhu J, Wang X, Yang F, Zhao L. A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching. 在 Jia Y, Zhang W, Fu Y, Wang J, 编辑, Proceedings of 2023 Chinese Intelligent Systems Conference - Volume I. Springer Science and Business Media Deutschland GmbH. 2023. 页码 607-616. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-99-6847-3_52

A Visual-LiDAR Object Tracking Method Using Correlation Filter and Potential Matching

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此