Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping

Fei Wang; Chao Sun; Guoqi Zhong; Weiqiang Liang

doi:10.1109/EECR56827.2023.10150083

Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping

Fei Wang
, Chao Sun^*
, Guoqi Zhong
, Weiqiang Liang

^*Corresponding author for this work

School of Mechanical Engineering

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

1 Citation (Scopus)

Abstract

For autonomous vehicles, Simultaneous localization and mapping (SLAM) is one of the fundamental capabilities. Accurate and reliable SLAM are important for autonomous vehicles. In this work, we propose a novel LiDAR odometry and mapping method assisted by semantic segmentation and moving object segmentation. First, to acquire semantic information of point clouds and distinguish moving objects, a framework for segmenting LiDAR point clouds is proposed. Then an effective method for integrating semantic information and moving object information into feature-based LiDAR SLAM is proposed. With the assistance of semantic information and moving object information, moving points are filtered out, and semantic constrains are added in feature extraction and pose estimation to improve the localization accuracy. The experiment results on public datasets show that, compared to the baseline, the average relative pose estimation error of our proposed method is reduced by21.4% in rotation and 29.4% in translation.

Original language	English
Title of host publication	2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	267-273
Number of pages	7
ISBN (Electronic)	9781665491204
DOIs	https://doi.org/10.1109/EECR56827.2023.10150083
Publication status	Published - 2023
Event	9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023 - Wuhan, China Duration: 24 Feb 2023 → 26 Feb 2023

Publication series

Name	2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023

Conference

Conference	9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023
Country/Territory	China
City	Wuhan
Period	24/02/23 → 26/02/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

LiDAR SLAM
autonomous vehicles
convolutional neural networks
moving object segmentation
semantic segmentation

Access to Document

10.1109/EECR56827.2023.10150083

Cite this

Wang, F., Sun, C., Zhong, G., & Liang, W. (2023). Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping. In 2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023 (pp. 267-273). (2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EECR56827.2023.10150083

Wang, Fei ; Sun, Chao ; Zhong, Guoqi et al. / Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping. 2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 267-273 (2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023).

@inproceedings{0db2e34c40ce4824a0f5306676883b53,

title = "Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping",

abstract = "For autonomous vehicles, Simultaneous localization and mapping (SLAM) is one of the fundamental capabilities. Accurate and reliable SLAM are important for autonomous vehicles. In this work, we propose a novel LiDAR odometry and mapping method assisted by semantic segmentation and moving object segmentation. First, to acquire semantic information of point clouds and distinguish moving objects, a framework for segmenting LiDAR point clouds is proposed. Then an effective method for integrating semantic information and moving object information into feature-based LiDAR SLAM is proposed. With the assistance of semantic information and moving object information, moving points are filtered out, and semantic constrains are added in feature extraction and pose estimation to improve the localization accuracy. The experiment results on public datasets show that, compared to the baseline, the average relative pose estimation error of our proposed method is reduced by21.4\% in rotation and 29.4\% in translation.",

keywords = "LiDAR SLAM, autonomous vehicles, convolutional neural networks, moving object segmentation, semantic segmentation",

author = "Fei Wang and Chao Sun and Guoqi Zhong and Weiqiang Liang",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023 ; Conference date: 24-02-2023 Through 26-02-2023",

year = "2023",

doi = "10.1109/EECR56827.2023.10150083",

language = "English",

series = "2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "267--273",

booktitle = "2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023",

address = "United States",

}

Wang, F, Sun, C, Zhong, G & Liang, W 2023, Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping. in 2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023. 2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023, Institute of Electrical and Electronics Engineers Inc., pp. 267-273, 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023, Wuhan, China, 24/02/23. https://doi.org/10.1109/EECR56827.2023.10150083

Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping. / Wang, Fei; Sun, Chao; Zhong, Guoqi et al.
2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 267-273 (2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023).

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

TY - GEN

T1 - Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping

AU - Wang, Fei

AU - Sun, Chao

AU - Zhong, Guoqi

AU - Liang, Weiqiang

PY - 2023

Y1 - 2023

N2 - For autonomous vehicles, Simultaneous localization and mapping (SLAM) is one of the fundamental capabilities. Accurate and reliable SLAM are important for autonomous vehicles. In this work, we propose a novel LiDAR odometry and mapping method assisted by semantic segmentation and moving object segmentation. First, to acquire semantic information of point clouds and distinguish moving objects, a framework for segmenting LiDAR point clouds is proposed. Then an effective method for integrating semantic information and moving object information into feature-based LiDAR SLAM is proposed. With the assistance of semantic information and moving object information, moving points are filtered out, and semantic constrains are added in feature extraction and pose estimation to improve the localization accuracy. The experiment results on public datasets show that, compared to the baseline, the average relative pose estimation error of our proposed method is reduced by21.4% in rotation and 29.4% in translation.

AB - For autonomous vehicles, Simultaneous localization and mapping (SLAM) is one of the fundamental capabilities. Accurate and reliable SLAM are important for autonomous vehicles. In this work, we propose a novel LiDAR odometry and mapping method assisted by semantic segmentation and moving object segmentation. First, to acquire semantic information of point clouds and distinguish moving objects, a framework for segmenting LiDAR point clouds is proposed. Then an effective method for integrating semantic information and moving object information into feature-based LiDAR SLAM is proposed. With the assistance of semantic information and moving object information, moving points are filtered out, and semantic constrains are added in feature extraction and pose estimation to improve the localization accuracy. The experiment results on public datasets show that, compared to the baseline, the average relative pose estimation error of our proposed method is reduced by21.4% in rotation and 29.4% in translation.

KW - LiDAR SLAM

KW - autonomous vehicles

KW - convolutional neural networks

KW - moving object segmentation

KW - semantic segmentation

UR - https://www.scopus.com/pages/publications/85164261060

U2 - 10.1109/EECR56827.2023.10150083

DO - 10.1109/EECR56827.2023.10150083

M3 - Conference contribution

AN - SCOPUS:85164261060

T3 - 2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023

SP - 267

EP - 273

BT - 2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023

Y2 - 24 February 2023 through 26 February 2023

ER -

Wang F, Sun C, Zhong G, Liang W. Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping. In 2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 267-273. (2023 9th International Conference on Electrical Engineering, Control and Robotics, EECR 2023). doi: 10.1109/EECR56827.2023.10150083

Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this