Cargando…
A Robust Parallel Initialization Method for Monocular Visual-Inertial SLAM
In order to improve the initialization robustness of visual inertial SLAM, the complementarity of the optical flow method and the feature-based method can be used in vision data processing. The parallel initialization method is proposed, where the optical flow inertial initialization and the monocul...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9657975/ https://www.ncbi.nlm.nih.gov/pubmed/36366008 http://dx.doi.org/10.3390/s22218307 |
_version_ | 1784829834380181504 |
---|---|
author | Zhong, Min Yao, Yiqing Xu, Xiaosu Wei, Hongyu |
author_facet | Zhong, Min Yao, Yiqing Xu, Xiaosu Wei, Hongyu |
author_sort | Zhong, Min |
collection | PubMed |
description | In order to improve the initialization robustness of visual inertial SLAM, the complementarity of the optical flow method and the feature-based method can be used in vision data processing. The parallel initialization method is proposed, where the optical flow inertial initialization and the monocular feature-based initialization are carried out at the same time. After the initializations, the state estimation results are jointly optimized by bundle adjustment. The proposed method retains more mapping information, and correspondingly is more adaptable to the initialization scene. It is found that the initialization map constructed by the proposed method features a comparable accuracy to the one constructed by ORB-SLAM3 in monocular inertial mode. Since the online extrinsic parameter estimation can be realized by the proposed method, it is considered better than ORB-SLAM3 in the aspect of portability. By the experiments performed on the benchmark dataset EuRoC, the effectiveness and robustness of the proposed method are validated. |
format | Online Article Text |
id | pubmed-9657975 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96579752022-11-15 A Robust Parallel Initialization Method for Monocular Visual-Inertial SLAM Zhong, Min Yao, Yiqing Xu, Xiaosu Wei, Hongyu Sensors (Basel) Article In order to improve the initialization robustness of visual inertial SLAM, the complementarity of the optical flow method and the feature-based method can be used in vision data processing. The parallel initialization method is proposed, where the optical flow inertial initialization and the monocular feature-based initialization are carried out at the same time. After the initializations, the state estimation results are jointly optimized by bundle adjustment. The proposed method retains more mapping information, and correspondingly is more adaptable to the initialization scene. It is found that the initialization map constructed by the proposed method features a comparable accuracy to the one constructed by ORB-SLAM3 in monocular inertial mode. Since the online extrinsic parameter estimation can be realized by the proposed method, it is considered better than ORB-SLAM3 in the aspect of portability. By the experiments performed on the benchmark dataset EuRoC, the effectiveness and robustness of the proposed method are validated. MDPI 2022-10-29 /pmc/articles/PMC9657975/ /pubmed/36366008 http://dx.doi.org/10.3390/s22218307 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Zhong, Min Yao, Yiqing Xu, Xiaosu Wei, Hongyu A Robust Parallel Initialization Method for Monocular Visual-Inertial SLAM |
title | A Robust Parallel Initialization Method for Monocular Visual-Inertial SLAM |
title_full | A Robust Parallel Initialization Method for Monocular Visual-Inertial SLAM |
title_fullStr | A Robust Parallel Initialization Method for Monocular Visual-Inertial SLAM |
title_full_unstemmed | A Robust Parallel Initialization Method for Monocular Visual-Inertial SLAM |
title_short | A Robust Parallel Initialization Method for Monocular Visual-Inertial SLAM |
title_sort | robust parallel initialization method for monocular visual-inertial slam |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9657975/ https://www.ncbi.nlm.nih.gov/pubmed/36366008 http://dx.doi.org/10.3390/s22218307 |
work_keys_str_mv | AT zhongmin arobustparallelinitializationmethodformonocularvisualinertialslam AT yaoyiqing arobustparallelinitializationmethodformonocularvisualinertialslam AT xuxiaosu arobustparallelinitializationmethodformonocularvisualinertialslam AT weihongyu arobustparallelinitializationmethodformonocularvisualinertialslam AT zhongmin robustparallelinitializationmethodformonocularvisualinertialslam AT yaoyiqing robustparallelinitializationmethodformonocularvisualinertialslam AT xuxiaosu robustparallelinitializationmethodformonocularvisualinertialslam AT weihongyu robustparallelinitializationmethodformonocularvisualinertialslam |