A ROBUST METHOD FOR STEREO VISUAL ODOMETRY BASED ON MULTIPLE EUCLIDEAN DISTANCE CONSTRAINT AND RANSAC ALGORITHM
Visual Odometry (VO) is a critical component for planetary robot navigation and safety. It estimates the ego-motion using stereo images frame by frame. Feature points extraction and matching is one of the key steps for robotic motion estimation which largely influences the precision and robustness....
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2017-07-01
|
Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3-W1/219/2017/isprs-archives-XLII-3-W1-219-2017.pdf |
id |
doaj-eca3d325505d4ce28df4e79553eae879 |
---|---|
record_format |
Article |
spelling |
doaj-eca3d325505d4ce28df4e79553eae8792020-11-24T21:40:04ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342017-07-01XLII-3-W121922410.5194/isprs-archives-XLII-3-W1-219-2017A ROBUST METHOD FOR STEREO VISUAL ODOMETRY BASED ON MULTIPLE EUCLIDEAN DISTANCE CONSTRAINT AND RANSAC ALGORITHMQ. Zhou0X. Tong1S. Liu2X. Lu3S. Liu4P. Chen5Y. Jin6H. Xie7College of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaChina International Engineering Consulting Corporation, Beijing, ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaVisual Odometry (VO) is a critical component for planetary robot navigation and safety. It estimates the ego-motion using stereo images frame by frame. Feature points extraction and matching is one of the key steps for robotic motion estimation which largely influences the precision and robustness. In this work, we choose the Oriented FAST and Rotated BRIEF (ORB) features by considering both accuracy and speed issues. For more robustness in challenging environment e.g., rough terrain or planetary surface, this paper presents a robust outliers elimination method based on Euclidean Distance Constraint (EDC) and Random Sample Consensus (RANSAC) algorithm. In the matching process, a set of ORB feature points are extracted from the current left and right synchronous images and the Brute Force (BF) matcher is used to find the correspondences between the two images for the Space Intersection. Then the EDC and RANSAC algorithms are carried out to eliminate mismatches whose distances are beyond a predefined threshold. Similarly, when the left image of the next time matches the feature points with the current left images, the EDC and RANSAC are iteratively performed. After the above mentioned, there are exceptional remaining mismatched points in some cases, for which the third time RANSAC is applied to eliminate the effects of those outliers in the estimation of the ego-motion parameters (Interior Orientation and Exterior Orientation). The proposed approach has been tested on a real-world vehicle dataset and the result benefits from its high robustness.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3-W1/219/2017/isprs-archives-XLII-3-W1-219-2017.pdf |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Q. Zhou X. Tong S. Liu X. Lu S. Liu P. Chen Y. Jin H. Xie |
spellingShingle |
Q. Zhou X. Tong S. Liu X. Lu S. Liu P. Chen Y. Jin H. Xie A ROBUST METHOD FOR STEREO VISUAL ODOMETRY BASED ON MULTIPLE EUCLIDEAN DISTANCE CONSTRAINT AND RANSAC ALGORITHM The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
author_facet |
Q. Zhou X. Tong S. Liu X. Lu S. Liu P. Chen Y. Jin H. Xie |
author_sort |
Q. Zhou |
title |
A ROBUST METHOD FOR STEREO VISUAL ODOMETRY BASED ON MULTIPLE EUCLIDEAN DISTANCE CONSTRAINT AND RANSAC ALGORITHM |
title_short |
A ROBUST METHOD FOR STEREO VISUAL ODOMETRY BASED ON MULTIPLE EUCLIDEAN DISTANCE CONSTRAINT AND RANSAC ALGORITHM |
title_full |
A ROBUST METHOD FOR STEREO VISUAL ODOMETRY BASED ON MULTIPLE EUCLIDEAN DISTANCE CONSTRAINT AND RANSAC ALGORITHM |
title_fullStr |
A ROBUST METHOD FOR STEREO VISUAL ODOMETRY BASED ON MULTIPLE EUCLIDEAN DISTANCE CONSTRAINT AND RANSAC ALGORITHM |
title_full_unstemmed |
A ROBUST METHOD FOR STEREO VISUAL ODOMETRY BASED ON MULTIPLE EUCLIDEAN DISTANCE CONSTRAINT AND RANSAC ALGORITHM |
title_sort |
robust method for stereo visual odometry based on multiple euclidean distance constraint and ransac algorithm |
publisher |
Copernicus Publications |
series |
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
issn |
1682-1750 2194-9034 |
publishDate |
2017-07-01 |
description |
Visual Odometry (VO) is a critical component for planetary robot navigation and safety. It estimates the ego-motion using stereo images frame by frame. Feature points extraction and matching is one of the key steps for robotic motion estimation which largely influences the precision and robustness. In this work, we choose the Oriented FAST and Rotated BRIEF (ORB) features by considering both accuracy and speed issues. For more robustness in challenging environment e.g., rough terrain or planetary surface, this paper presents a robust outliers elimination method based on Euclidean Distance Constraint (EDC) and Random Sample Consensus (RANSAC) algorithm. In the matching process, a set of ORB feature points are extracted from the current left and right synchronous images and the Brute Force (BF) matcher is used to find the correspondences between the two images for the Space Intersection. Then the EDC and RANSAC algorithms are carried out to eliminate mismatches whose distances are beyond a predefined threshold. Similarly, when the left image of the next time matches the feature points with the current left images, the EDC and RANSAC are iteratively performed. After the above mentioned, there are exceptional remaining mismatched points in some cases, for which the third time RANSAC is applied to eliminate the effects of those outliers in the estimation of the ego-motion parameters (Interior Orientation and Exterior Orientation). The proposed approach has been tested on a real-world vehicle dataset and the result benefits from its high robustness. |
url |
https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3-W1/219/2017/isprs-archives-XLII-3-W1-219-2017.pdf |
work_keys_str_mv |
AT qzhou arobustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT xtong arobustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT sliu arobustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT xlu arobustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT sliu arobustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT pchen arobustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT yjin arobustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT hxie arobustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT qzhou robustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT xtong robustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT sliu robustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT xlu robustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT sliu robustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT pchen robustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT yjin robustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm AT hxie robustmethodforstereovisualodometrybasedonmultipleeuclideandistanceconstraintandransacalgorithm |
_version_ |
1725928361922920448 |