Autonomous Vehicle Localization with Prior Visual Point Cloud Map Constraints in GNSS-Challenged Environments
Accurate vehicle ego-localization is key for autonomous vehicles to complete high-level navigation tasks. The state-of-the-art localization methods adopt visual and light detection and ranging (LiDAR) simultaneous localization and mapping (SLAM) to estimate the position of the vehicle. However, both...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/3/506 |
_version_ | 1797417329669177344 |
---|---|
author | Xiaohu Lin Fuhong Wang Bisheng Yang Wanwei Zhang |
author_facet | Xiaohu Lin Fuhong Wang Bisheng Yang Wanwei Zhang |
author_sort | Xiaohu Lin |
collection | DOAJ |
description | Accurate vehicle ego-localization is key for autonomous vehicles to complete high-level navigation tasks. The state-of-the-art localization methods adopt visual and light detection and ranging (LiDAR) simultaneous localization and mapping (SLAM) to estimate the position of the vehicle. However, both of them may suffer from error accumulation due to long-term running without loop optimization or prior constraints. Actually, the vehicle cannot always return to the revisited location, which will cause errors to accumulate in Global Navigation Satellite System (GNSS)-challenged environments. To solve this problem, we proposed a novel localization method with prior dense visual point cloud map constraints generated by a stereo camera. Firstly, the semi-global-block-matching (SGBM) algorithm is adopted to estimate the visual point cloud of each frame and stereo visual odometry is used to provide the initial position for the current visual point cloud. Secondly, multiple filtering and adaptive prior map segmentation are performed on the prior dense visual point cloud map for fast matching and localization. Then, the current visual point cloud is matched with the candidate sub-map by normal distribution transformation (NDT). Finally, the matching result is used to update pose prediction based on the last frame for accurate localization. Comprehensive experiments were undertaken to validate the proposed method, showing that the root mean square errors (RMSEs) of translation and rotation are less than 5.59 m and 0.08°, respectively. |
first_indexed | 2024-03-09T06:18:14Z |
format | Article |
id | doaj.art-e482620a58f1438885ec3d4929eb70e0 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T06:18:14Z |
publishDate | 2021-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-e482620a58f1438885ec3d4929eb70e02023-12-03T11:51:39ZengMDPI AGRemote Sensing2072-42922021-01-0113350610.3390/rs13030506Autonomous Vehicle Localization with Prior Visual Point Cloud Map Constraints in GNSS-Challenged EnvironmentsXiaohu Lin0Fuhong Wang1Bisheng Yang2Wanwei Zhang3School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaAccurate vehicle ego-localization is key for autonomous vehicles to complete high-level navigation tasks. The state-of-the-art localization methods adopt visual and light detection and ranging (LiDAR) simultaneous localization and mapping (SLAM) to estimate the position of the vehicle. However, both of them may suffer from error accumulation due to long-term running without loop optimization or prior constraints. Actually, the vehicle cannot always return to the revisited location, which will cause errors to accumulate in Global Navigation Satellite System (GNSS)-challenged environments. To solve this problem, we proposed a novel localization method with prior dense visual point cloud map constraints generated by a stereo camera. Firstly, the semi-global-block-matching (SGBM) algorithm is adopted to estimate the visual point cloud of each frame and stereo visual odometry is used to provide the initial position for the current visual point cloud. Secondly, multiple filtering and adaptive prior map segmentation are performed on the prior dense visual point cloud map for fast matching and localization. Then, the current visual point cloud is matched with the candidate sub-map by normal distribution transformation (NDT). Finally, the matching result is used to update pose prediction based on the last frame for accurate localization. Comprehensive experiments were undertaken to validate the proposed method, showing that the root mean square errors (RMSEs) of translation and rotation are less than 5.59 m and 0.08°, respectively.https://www.mdpi.com/2072-4292/13/3/506autonomous vehiclestereo visual odometrypose predictionaccurate vehicle localization |
spellingShingle | Xiaohu Lin Fuhong Wang Bisheng Yang Wanwei Zhang Autonomous Vehicle Localization with Prior Visual Point Cloud Map Constraints in GNSS-Challenged Environments Remote Sensing autonomous vehicle stereo visual odometry pose prediction accurate vehicle localization |
title | Autonomous Vehicle Localization with Prior Visual Point Cloud Map Constraints in GNSS-Challenged Environments |
title_full | Autonomous Vehicle Localization with Prior Visual Point Cloud Map Constraints in GNSS-Challenged Environments |
title_fullStr | Autonomous Vehicle Localization with Prior Visual Point Cloud Map Constraints in GNSS-Challenged Environments |
title_full_unstemmed | Autonomous Vehicle Localization with Prior Visual Point Cloud Map Constraints in GNSS-Challenged Environments |
title_short | Autonomous Vehicle Localization with Prior Visual Point Cloud Map Constraints in GNSS-Challenged Environments |
title_sort | autonomous vehicle localization with prior visual point cloud map constraints in gnss challenged environments |
topic | autonomous vehicle stereo visual odometry pose prediction accurate vehicle localization |
url | https://www.mdpi.com/2072-4292/13/3/506 |
work_keys_str_mv | AT xiaohulin autonomousvehiclelocalizationwithpriorvisualpointcloudmapconstraintsingnsschallengedenvironments AT fuhongwang autonomousvehiclelocalizationwithpriorvisualpointcloudmapconstraintsingnsschallengedenvironments AT bishengyang autonomousvehiclelocalizationwithpriorvisualpointcloudmapconstraintsingnsschallengedenvironments AT wanweizhang autonomousvehiclelocalizationwithpriorvisualpointcloudmapconstraintsingnsschallengedenvironments |