Simulation-Based Self-Supervised Line Extraction for LiDAR Odometry in Urban Road Scenes
LiDAR odometry is a fundamental task for high-precision map construction and real-time and accurate localization in autonomous driving. However, point clouds in urban road scenes acquired by vehicle-borne lasers are of large amounts, “near dense and far sparse” density, and contain different dynamic...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/22/5322 |
| _version_ | 1827638815745900544 |
|---|---|
| author | Peng Wang Ruqin Zhou Chenguang Dai Hanyun Wang Wanshou Jiang Yongsheng Zhang |
| author_facet | Peng Wang Ruqin Zhou Chenguang Dai Hanyun Wang Wanshou Jiang Yongsheng Zhang |
| author_sort | Peng Wang |
| collection | DOAJ |
| description | LiDAR odometry is a fundamental task for high-precision map construction and real-time and accurate localization in autonomous driving. However, point clouds in urban road scenes acquired by vehicle-borne lasers are of large amounts, “near dense and far sparse” density, and contain different dynamic objects, leading to low efficiency and low accuracy of existing LiDAR odometry methods. To address the above issues, a simulation-based self-supervised line extraction in urban road scene is proposed, as a pre-processing for LiDAR odometry to reduce the amount of input and the interference from dynamic objects. A simulated dataset is first constructed according to the characteristics of point clouds in urban road scenes; and then, an EdgeConv-based network, named LO-LineNet, is used for pre-training; finally, a model transferring strategy is adopted to transfer the pre-trained model from a simulated dataset to real-world scenes without ground-truth labels. Experimental results on the KITTI Odometry Dataset and the Apollo SouthBay Dataset indicate that the proposed method can accurately extract reliable lines in urban road scenes in a self-supervised way, and the use of the extracted reliable lines as input for odometry can significantly improve its accuracy and efficiency in urban road scenes. |
| first_indexed | 2024-03-09T16:29:07Z |
| format | Article |
| id | doaj.art-17e0bdd57a124808b243024bec10134b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T16:29:07Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-17e0bdd57a124808b243024bec10134b2023-11-24T15:04:23ZengMDPI AGRemote Sensing2072-42922023-11-011522532210.3390/rs15225322Simulation-Based Self-Supervised Line Extraction for LiDAR Odometry in Urban Road ScenesPeng Wang0Ruqin Zhou1Chenguang Dai2Hanyun Wang3Wanshou Jiang4Yongsheng Zhang5School of Surveying and Mapping, Information Engineering University, Zhengzhou 450001, ChinaSchool of Surveying and Mapping, Information Engineering University, Zhengzhou 450001, ChinaSchool of Surveying and Mapping, Information Engineering University, Zhengzhou 450001, ChinaSchool of Surveying and Mapping, Information Engineering University, Zhengzhou 450001, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaSchool of Surveying and Mapping, Information Engineering University, Zhengzhou 450001, ChinaLiDAR odometry is a fundamental task for high-precision map construction and real-time and accurate localization in autonomous driving. However, point clouds in urban road scenes acquired by vehicle-borne lasers are of large amounts, “near dense and far sparse” density, and contain different dynamic objects, leading to low efficiency and low accuracy of existing LiDAR odometry methods. To address the above issues, a simulation-based self-supervised line extraction in urban road scene is proposed, as a pre-processing for LiDAR odometry to reduce the amount of input and the interference from dynamic objects. A simulated dataset is first constructed according to the characteristics of point clouds in urban road scenes; and then, an EdgeConv-based network, named LO-LineNet, is used for pre-training; finally, a model transferring strategy is adopted to transfer the pre-trained model from a simulated dataset to real-world scenes without ground-truth labels. Experimental results on the KITTI Odometry Dataset and the Apollo SouthBay Dataset indicate that the proposed method can accurately extract reliable lines in urban road scenes in a self-supervised way, and the use of the extracted reliable lines as input for odometry can significantly improve its accuracy and efficiency in urban road scenes.https://www.mdpi.com/2072-4292/15/22/5322urban road sceneLiDAR odometryline extractionmodel transferring |
| spellingShingle | Peng Wang Ruqin Zhou Chenguang Dai Hanyun Wang Wanshou Jiang Yongsheng Zhang Simulation-Based Self-Supervised Line Extraction for LiDAR Odometry in Urban Road Scenes Remote Sensing urban road scene LiDAR odometry line extraction model transferring |
| title | Simulation-Based Self-Supervised Line Extraction for LiDAR Odometry in Urban Road Scenes |
| title_full | Simulation-Based Self-Supervised Line Extraction for LiDAR Odometry in Urban Road Scenes |
| title_fullStr | Simulation-Based Self-Supervised Line Extraction for LiDAR Odometry in Urban Road Scenes |
| title_full_unstemmed | Simulation-Based Self-Supervised Line Extraction for LiDAR Odometry in Urban Road Scenes |
| title_short | Simulation-Based Self-Supervised Line Extraction for LiDAR Odometry in Urban Road Scenes |
| title_sort | simulation based self supervised line extraction for lidar odometry in urban road scenes |
| topic | urban road scene LiDAR odometry line extraction model transferring |
| url | https://www.mdpi.com/2072-4292/15/22/5322 |
| work_keys_str_mv | AT pengwang simulationbasedselfsupervisedlineextractionforlidarodometryinurbanroadscenes AT ruqinzhou simulationbasedselfsupervisedlineextractionforlidarodometryinurbanroadscenes AT chenguangdai simulationbasedselfsupervisedlineextractionforlidarodometryinurbanroadscenes AT hanyunwang simulationbasedselfsupervisedlineextractionforlidarodometryinurbanroadscenes AT wanshoujiang simulationbasedselfsupervisedlineextractionforlidarodometryinurbanroadscenes AT yongshengzhang simulationbasedselfsupervisedlineextractionforlidarodometryinurbanroadscenes |