A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane Segmentation
Objects in satellite remote sensing image sequences often have large deformations, and the stereo matching of this kind of image is so difficult that the matching rate generally drops. A disparity refinement method is needed to correct and fill the disparity. A method for disparity refinement based...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-05-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/10/1903 |
id |
doaj-383571edcd3b46d2b3dfd6c938c21751 |
---|---|
record_format |
Article |
spelling |
doaj-383571edcd3b46d2b3dfd6c938c217512021-05-31T23:55:16ZengMDPI AGRemote Sensing2072-42922021-05-01131903190310.3390/rs13101903A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane SegmentationZhihui Li0Jiaxin Liu1Yang Yang2Jing Zhang3School of Computer Science and Technology, Harbin Engineering University, Harbin 150001, ChinaSchool of Computer Science and Technology, Harbin Engineering University, Harbin 150001, ChinaSchool of Computer Science and Technology, Harbin Engineering University, Harbin 150001, ChinaSchool of Information Science and Engineering, University of Jinan, Jinan 250022, ChinaObjects in satellite remote sensing image sequences often have large deformations, and the stereo matching of this kind of image is so difficult that the matching rate generally drops. A disparity refinement method is needed to correct and fill the disparity. A method for disparity refinement based on the results of plane segmentation is proposed in this paper. The plane segmentation algorithm includes two steps: Initial segmentation based on mean-shift and alpha-expansion-based energy minimization. According to the results of plane segmentation and fitting, the disparity is refined by filling missed matching regions and removing outliers. The experimental results showed that the proposed plane segmentation method could not only accurately fit the plane in the presence of noise but also approximate the surface by plane combination. After the proposed plane segmentation method was applied to the disparity refinement of remote sensing images, many missed matches were filled, and the elevation errors were reduced. This proved that the proposed algorithm was effective. For difficult evaluations resulting from significant variations in remote sensing images of different satellites, the edge matching rate and the edge matching map are proposed as new stereo matching evaluation and analysis tools. Experiment results showed that they were easy to use, intuitive, and effective.https://www.mdpi.com/2072-4292/13/10/1903disparity refinementthree-dimensional reconstructionremote sensing image |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhihui Li Jiaxin Liu Yang Yang Jing Zhang |
spellingShingle |
Zhihui Li Jiaxin Liu Yang Yang Jing Zhang A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane Segmentation Remote Sensing disparity refinement three-dimensional reconstruction remote sensing image |
author_facet |
Zhihui Li Jiaxin Liu Yang Yang Jing Zhang |
author_sort |
Zhihui Li |
title |
A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane Segmentation |
title_short |
A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane Segmentation |
title_full |
A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane Segmentation |
title_fullStr |
A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane Segmentation |
title_full_unstemmed |
A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane Segmentation |
title_sort |
disparity refinement algorithm for satellite remote sensing images based on mean-shift plane segmentation |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2021-05-01 |
description |
Objects in satellite remote sensing image sequences often have large deformations, and the stereo matching of this kind of image is so difficult that the matching rate generally drops. A disparity refinement method is needed to correct and fill the disparity. A method for disparity refinement based on the results of plane segmentation is proposed in this paper. The plane segmentation algorithm includes two steps: Initial segmentation based on mean-shift and alpha-expansion-based energy minimization. According to the results of plane segmentation and fitting, the disparity is refined by filling missed matching regions and removing outliers. The experimental results showed that the proposed plane segmentation method could not only accurately fit the plane in the presence of noise but also approximate the surface by plane combination. After the proposed plane segmentation method was applied to the disparity refinement of remote sensing images, many missed matches were filled, and the elevation errors were reduced. This proved that the proposed algorithm was effective. For difficult evaluations resulting from significant variations in remote sensing images of different satellites, the edge matching rate and the edge matching map are proposed as new stereo matching evaluation and analysis tools. Experiment results showed that they were easy to use, intuitive, and effective. |
topic |
disparity refinement three-dimensional reconstruction remote sensing image |
url |
https://www.mdpi.com/2072-4292/13/10/1903 |
work_keys_str_mv |
AT zhihuili adisparityrefinementalgorithmforsatelliteremotesensingimagesbasedonmeanshiftplanesegmentation AT jiaxinliu adisparityrefinementalgorithmforsatelliteremotesensingimagesbasedonmeanshiftplanesegmentation AT yangyang adisparityrefinementalgorithmforsatelliteremotesensingimagesbasedonmeanshiftplanesegmentation AT jingzhang adisparityrefinementalgorithmforsatelliteremotesensingimagesbasedonmeanshiftplanesegmentation AT zhihuili disparityrefinementalgorithmforsatelliteremotesensingimagesbasedonmeanshiftplanesegmentation AT jiaxinliu disparityrefinementalgorithmforsatelliteremotesensingimagesbasedonmeanshiftplanesegmentation AT yangyang disparityrefinementalgorithmforsatelliteremotesensingimagesbasedonmeanshiftplanesegmentation AT jingzhang disparityrefinementalgorithmforsatelliteremotesensingimagesbasedonmeanshiftplanesegmentation |
_version_ |
1721416202058727424 |