Semantic SLAM With More Accurate Point Cloud Map in Dynamic Environments
Static environment is a prerequisite for most existing vision-based SLAM (simultaneous localization and mapping) systems to work properly, which greatly limits the use of SLAM in real-world environments. The quality of the global point cloud map constructed by the SLAM system in a dynamic environmen...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9119407/ |
id |
doaj-9fff89b88a4543109f7943106d08d966 |
---|---|
record_format |
Article |
spelling |
doaj-9fff89b88a4543109f7943106d08d9662021-03-30T02:28:02ZengIEEEIEEE Access2169-35362020-01-01811223711225210.1109/ACCESS.2020.30031609119407Semantic SLAM With More Accurate Point Cloud Map in Dynamic EnvironmentsYingchun Fan0https://orcid.org/0000-0003-0661-2545Qichi Zhang1https://orcid.org/0000-0003-1139-4570Shaofeng Liu2https://orcid.org/0000-0002-8968-4060Yuliang Tang3https://orcid.org/0000-0001-5609-6847Xin Jing4https://orcid.org/0000-0003-3407-7551Jintao Yao5https://orcid.org/0000-0002-8344-5632Hong Han6https://orcid.org/0000-0002-8019-3740School of Artificial Intelligence, Xidian University, Xi’an, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an, ChinaShaanxi Key Laboratory of Integrated and Intelligent Navigation, Xi’an, ChinaShaanxi Key Laboratory of Integrated and Intelligent Navigation, Xi’an, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an, ChinaStatic environment is a prerequisite for most existing vision-based SLAM (simultaneous localization and mapping) systems to work properly, which greatly limits the use of SLAM in real-world environments. The quality of the global point cloud map constructed by the SLAM system in a dynamic environment is related to the camera pose estimation and the removal of noise blocks in the local point cloud maps. Most dynamic SLAM systems mainly improve the accuracy of camera localization, but rarely study on noise blocks removal. In this paper, we proposed a novel semantic SLAM system with a more accurate point cloud map in dynamic environments. We obtained the masks and bounding boxes of the dynamic objects in the images by BlitzNet. The mask of a dynamic object was extended by analyzing the depth statistical information of the mask in the bounding box. The islands generated by the residual information of dynamic objects were removed by a morphological operation after geometric segmentation. With the bounding boxes, the images can be quickly divided into environment regions and dynamic regions, so the depth-stable matching points in the environment regions are used to construct epipolar constraints to locate the static matching points in the dynamic regions. In order to verify the preference of our proposed SLAM system, we conduct the experiments on the TUM RGB-D datasets. Compared with the state-of-the-art dynamic SLAM systems, the global point cloud map constructed by our system is the best.https://ieeexplore.ieee.org/document/9119407/Dynamic environmentglobal point cloud mapnoise blockssemantic SLAM |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yingchun Fan Qichi Zhang Shaofeng Liu Yuliang Tang Xin Jing Jintao Yao Hong Han |
spellingShingle |
Yingchun Fan Qichi Zhang Shaofeng Liu Yuliang Tang Xin Jing Jintao Yao Hong Han Semantic SLAM With More Accurate Point Cloud Map in Dynamic Environments IEEE Access Dynamic environment global point cloud map noise blocks semantic SLAM |
author_facet |
Yingchun Fan Qichi Zhang Shaofeng Liu Yuliang Tang Xin Jing Jintao Yao Hong Han |
author_sort |
Yingchun Fan |
title |
Semantic SLAM With More Accurate Point Cloud Map in Dynamic Environments |
title_short |
Semantic SLAM With More Accurate Point Cloud Map in Dynamic Environments |
title_full |
Semantic SLAM With More Accurate Point Cloud Map in Dynamic Environments |
title_fullStr |
Semantic SLAM With More Accurate Point Cloud Map in Dynamic Environments |
title_full_unstemmed |
Semantic SLAM With More Accurate Point Cloud Map in Dynamic Environments |
title_sort |
semantic slam with more accurate point cloud map in dynamic environments |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Static environment is a prerequisite for most existing vision-based SLAM (simultaneous localization and mapping) systems to work properly, which greatly limits the use of SLAM in real-world environments. The quality of the global point cloud map constructed by the SLAM system in a dynamic environment is related to the camera pose estimation and the removal of noise blocks in the local point cloud maps. Most dynamic SLAM systems mainly improve the accuracy of camera localization, but rarely study on noise blocks removal. In this paper, we proposed a novel semantic SLAM system with a more accurate point cloud map in dynamic environments. We obtained the masks and bounding boxes of the dynamic objects in the images by BlitzNet. The mask of a dynamic object was extended by analyzing the depth statistical information of the mask in the bounding box. The islands generated by the residual information of dynamic objects were removed by a morphological operation after geometric segmentation. With the bounding boxes, the images can be quickly divided into environment regions and dynamic regions, so the depth-stable matching points in the environment regions are used to construct epipolar constraints to locate the static matching points in the dynamic regions. In order to verify the preference of our proposed SLAM system, we conduct the experiments on the TUM RGB-D datasets. Compared with the state-of-the-art dynamic SLAM systems, the global point cloud map constructed by our system is the best. |
topic |
Dynamic environment global point cloud map noise blocks semantic SLAM |
url |
https://ieeexplore.ieee.org/document/9119407/ |
work_keys_str_mv |
AT yingchunfan semanticslamwithmoreaccuratepointcloudmapindynamicenvironments AT qichizhang semanticslamwithmoreaccuratepointcloudmapindynamicenvironments AT shaofengliu semanticslamwithmoreaccuratepointcloudmapindynamicenvironments AT yuliangtang semanticslamwithmoreaccuratepointcloudmapindynamicenvironments AT xinjing semanticslamwithmoreaccuratepointcloudmapindynamicenvironments AT jintaoyao semanticslamwithmoreaccuratepointcloudmapindynamicenvironments AT honghan semanticslamwithmoreaccuratepointcloudmapindynamicenvironments |
_version_ |
1724185098783293440 |