RGB-D SLAM with Manhattan Frame Estimation Using Orientation Relevance
Due to image noise, image blur, and inconsistency between depth data and color image, the accuracy and robustness of the pairwise spatial transformation computed by matching extracted features of detected key points in existing sparse Red Green Blue-Depth (RGB-D) Simultaneously Localization And Mapp...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/19/5/1050 |
_version_ | 1798005445583962112 |
---|---|
author | Liang Wang Zhiqiu Wu |
author_facet | Liang Wang Zhiqiu Wu |
author_sort | Liang Wang |
collection | DOAJ |
description | Due to image noise, image blur, and inconsistency between depth data and color image, the accuracy and robustness of the pairwise spatial transformation computed by matching extracted features of detected key points in existing sparse Red Green Blue-Depth (RGB-D) Simultaneously Localization And Mapping (SLAM) algorithms are poor. Considering that most indoor environments follow the Manhattan World assumption and the Manhattan Frame can be used as a reference to compute the pairwise spatial transformation, a new RGB-D SLAM algorithm is proposed. It first performs the Manhattan Frame Estimation using the introduced concept of orientation relevance. Then the pairwise spatial transformation between two RGB-D frames is computed with the Manhattan Frame Estimation. Finally, the Manhattan Frame Estimation using orientation relevance is incorporated into the RGB-D SLAM to improve its performance. Experimental results show that the proposed RGB-D SLAM algorithm has definite improvements in accuracy, robustness, and runtime. |
first_indexed | 2024-04-11T12:39:21Z |
format | Article |
id | doaj.art-ea4f6c9b30af4d46a818f887d95ec06c |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T12:39:21Z |
publishDate | 2019-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-ea4f6c9b30af4d46a818f887d95ec06c2022-12-22T04:23:32ZengMDPI AGSensors1424-82202019-03-01195105010.3390/s19051050s19051050RGB-D SLAM with Manhattan Frame Estimation Using Orientation RelevanceLiang Wang0Zhiqiu Wu1College of Automation, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaCollege of Automation, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaDue to image noise, image blur, and inconsistency between depth data and color image, the accuracy and robustness of the pairwise spatial transformation computed by matching extracted features of detected key points in existing sparse Red Green Blue-Depth (RGB-D) Simultaneously Localization And Mapping (SLAM) algorithms are poor. Considering that most indoor environments follow the Manhattan World assumption and the Manhattan Frame can be used as a reference to compute the pairwise spatial transformation, a new RGB-D SLAM algorithm is proposed. It first performs the Manhattan Frame Estimation using the introduced concept of orientation relevance. Then the pairwise spatial transformation between two RGB-D frames is computed with the Manhattan Frame Estimation. Finally, the Manhattan Frame Estimation using orientation relevance is incorporated into the RGB-D SLAM to improve its performance. Experimental results show that the proposed RGB-D SLAM algorithm has definite improvements in accuracy, robustness, and runtime.http://www.mdpi.com/1424-8220/19/5/1050SLAMRGB-Dindoor environmentManhattan frame estimationorientation relevancespatial transformation |
spellingShingle | Liang Wang Zhiqiu Wu RGB-D SLAM with Manhattan Frame Estimation Using Orientation Relevance Sensors SLAM RGB-D indoor environment Manhattan frame estimation orientation relevance spatial transformation |
title | RGB-D SLAM with Manhattan Frame Estimation Using Orientation Relevance |
title_full | RGB-D SLAM with Manhattan Frame Estimation Using Orientation Relevance |
title_fullStr | RGB-D SLAM with Manhattan Frame Estimation Using Orientation Relevance |
title_full_unstemmed | RGB-D SLAM with Manhattan Frame Estimation Using Orientation Relevance |
title_short | RGB-D SLAM with Manhattan Frame Estimation Using Orientation Relevance |
title_sort | rgb d slam with manhattan frame estimation using orientation relevance |
topic | SLAM RGB-D indoor environment Manhattan frame estimation orientation relevance spatial transformation |
url | http://www.mdpi.com/1424-8220/19/5/1050 |
work_keys_str_mv | AT liangwang rgbdslamwithmanhattanframeestimationusingorientationrelevance AT zhiqiuwu rgbdslamwithmanhattanframeestimationusingorientationrelevance |