A Robust Visual-Inertial Odometry Leveraging Point and Structural Line Features

Yumin Liu; Zhihao Cai; Jiawei Ji; Jiang Zhao; Yingxun Wang

doi:10.1007/978-981-96-2204-7_25

A Robust Visual-Inertial Odometry Leveraging Point and Structural Line Features

Yumin Liu
, Zhihao Cai^*
, Jiawei Ji
, Jiang Zhao
, Yingxun Wang

^*Corresponding author for this work

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper presents a robust Visual-Inertial Odometry that leverages point and structural line features for complex environments with lighting changes, low textures or repetitive textures. Firstly, a front-end with structural line features is designed. Based on the Atlanta World hypothesis, structural line parameterization, extraction, and triangulation methods are proposed for lines with vertical and horizontal direction; Secondly, a non-linear optimization back-end based on sliding-window is carried out, which is tightly coupled with structural line residual. Finally, the localization accuracy of the odometry is verified through real-world experiments.

Original language	English
Title of host publication	Advances in Guidance, Navigation and Control - Proceedings of 2024 International Conference on Guidance, Navigation and Control Volume 2
Editors	Liang Yan, Haibin Duan, Yimin Deng
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	257-267
Number of pages	11
ISBN (Print)	9789819622030
DOIs	https://doi.org/10.1007/978-981-96-2204-7_25
State	Published - 2025
Event	International Conference on Guidance, Navigation and Control, ICGNC 2024 - Changsha, China Duration: 9 Aug 2024 → 11 Aug 2024

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1338 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	International Conference on Guidance, Navigation and Control, ICGNC 2024
Country/Territory	China
City	Changsha
Period	9/08/24 → 11/08/24

Keywords

point-line fusion
structural line
visual-inertial odometry

Access to Document

10.1007/978-981-96-2204-7_25

Cite this

Liu, Y., Cai, Z., Ji, J., Zhao, J., & Wang, Y. (2025). A Robust Visual-Inertial Odometry Leveraging Point and Structural Line Features. In L. Yan, H. Duan, & Y. Deng (Eds.), Advances in Guidance, Navigation and Control - Proceedings of 2024 International Conference on Guidance, Navigation and Control Volume 2 (pp. 257-267). (Lecture Notes in Electrical Engineering; Vol. 1338 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-96-2204-7_25

Liu, Yumin ; Cai, Zhihao ; Ji, Jiawei et al. / A Robust Visual-Inertial Odometry Leveraging Point and Structural Line Features. Advances in Guidance, Navigation and Control - Proceedings of 2024 International Conference on Guidance, Navigation and Control Volume 2. editor / Liang Yan ; Haibin Duan ; Yimin Deng. Springer Science and Business Media Deutschland GmbH, 2025. pp. 257-267 (Lecture Notes in Electrical Engineering).

@inproceedings{6372be45d6254de2b9053cc73620b910,

title = "A Robust Visual-Inertial Odometry Leveraging Point and Structural Line Features",

abstract = "This paper presents a robust Visual-Inertial Odometry that leverages point and structural line features for complex environments with lighting changes, low textures or repetitive textures. Firstly, a front-end with structural line features is designed. Based on the Atlanta World hypothesis, structural line parameterization, extraction, and triangulation methods are proposed for lines with vertical and horizontal direction; Secondly, a non-linear optimization back-end based on sliding-window is carried out, which is tightly coupled with structural line residual. Finally, the localization accuracy of the odometry is verified through real-world experiments.",

keywords = "point-line fusion, structural line, visual-inertial odometry",

author = "Yumin Liu and Zhihao Cai and Jiawei Ji and Jiang Zhao and Yingxun Wang",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; International Conference on Guidance, Navigation and Control, ICGNC 2024 ; Conference date: 09-08-2024 Through 11-08-2024",

year = "2025",

doi = "10.1007/978-981-96-2204-7\_25",

language = "英语",

isbn = "9789819622030",

series = "Lecture Notes in Electrical Engineering",

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

pages = "257--267",

editor = "Liang Yan and Haibin Duan and Yimin Deng",

booktitle = "Advances in Guidance, Navigation and Control - Proceedings of 2024 International Conference on Guidance, Navigation and Control Volume 2",

address = "德国",

}

Liu, Y, Cai, Z, Ji, J, Zhao, J & Wang, Y 2025, A Robust Visual-Inertial Odometry Leveraging Point and Structural Line Features. in L Yan, H Duan & Y Deng (eds), Advances in Guidance, Navigation and Control - Proceedings of 2024 International Conference on Guidance, Navigation and Control Volume 2. Lecture Notes in Electrical Engineering, vol. 1338 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 257-267, International Conference on Guidance, Navigation and Control, ICGNC 2024, Changsha, China, 9/08/24. https://doi.org/10.1007/978-981-96-2204-7_25

A Robust Visual-Inertial Odometry Leveraging Point and Structural Line Features. / Liu, Yumin; Cai, Zhihao; Ji, Jiawei et al.
Advances in Guidance, Navigation and Control - Proceedings of 2024 International Conference on Guidance, Navigation and Control Volume 2. ed. / Liang Yan; Haibin Duan; Yimin Deng. Springer Science and Business Media Deutschland GmbH, 2025. p. 257-267 (Lecture Notes in Electrical Engineering; Vol. 1338 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Robust Visual-Inertial Odometry Leveraging Point and Structural Line Features

AU - Liu, Yumin

AU - Cai, Zhihao

AU - Ji, Jiawei

AU - Zhao, Jiang

AU - Wang, Yingxun

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

PY - 2025

Y1 - 2025

N2 - This paper presents a robust Visual-Inertial Odometry that leverages point and structural line features for complex environments with lighting changes, low textures or repetitive textures. Firstly, a front-end with structural line features is designed. Based on the Atlanta World hypothesis, structural line parameterization, extraction, and triangulation methods are proposed for lines with vertical and horizontal direction; Secondly, a non-linear optimization back-end based on sliding-window is carried out, which is tightly coupled with structural line residual. Finally, the localization accuracy of the odometry is verified through real-world experiments.

AB - This paper presents a robust Visual-Inertial Odometry that leverages point and structural line features for complex environments with lighting changes, low textures or repetitive textures. Firstly, a front-end with structural line features is designed. Based on the Atlanta World hypothesis, structural line parameterization, extraction, and triangulation methods are proposed for lines with vertical and horizontal direction; Secondly, a non-linear optimization back-end based on sliding-window is carried out, which is tightly coupled with structural line residual. Finally, the localization accuracy of the odometry is verified through real-world experiments.

KW - point-line fusion

KW - structural line

KW - visual-inertial odometry

UR - https://www.scopus.com/pages/publications/105000829006

U2 - 10.1007/978-981-96-2204-7_25

DO - 10.1007/978-981-96-2204-7_25

M3 - 会议稿件

AN - SCOPUS:105000829006

SN - 9789819622030

T3 - Lecture Notes in Electrical Engineering

SP - 257

EP - 267

BT - Advances in Guidance, Navigation and Control - Proceedings of 2024 International Conference on Guidance, Navigation and Control Volume 2

A2 - Yan, Liang

A2 - Duan, Haibin

A2 - Deng, Yimin

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Conference on Guidance, Navigation and Control, ICGNC 2024

Y2 - 9 August 2024 through 11 August 2024

ER -

Liu Y, Cai Z, Ji J, Zhao J , Wang Y. A Robust Visual-Inertial Odometry Leveraging Point and Structural Line Features. In Yan L, Duan H, Deng Y, editors, Advances in Guidance, Navigation and Control - Proceedings of 2024 International Conference on Guidance, Navigation and Control Volume 2. Springer Science and Business Media Deutschland GmbH. 2025. p. 257-267. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-96-2204-7_25