MULTI-SOURCE MULTI-SCALE HIERARCHICAL CONDITIONAL RANDOM FIELD MODEL FOR REMOTE SENSING IMAGE CLASSIFICATION
Fusion of remote sensing images and LiDAR data provides complimentary information for the remote sensing applications, such as object classification and recognition. In this paper, we propose a novel multi-source multi-scale hierarchical conditional random field (MSMSH-CRF) model to integrate featur...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2015-03-01
|
Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W4/293/2015/isprsannals-II-3-W4-293-2015.pdf |
id |
doaj-af9e32cd1f614996a7ee9d93c0ae785a |
---|---|
record_format |
Article |
spelling |
doaj-af9e32cd1f614996a7ee9d93c0ae785a2020-11-24T21:22:33ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502015-03-01II-3/W429330010.5194/isprsannals-II-3-W4-293-2015MULTI-SOURCE MULTI-SCALE HIERARCHICAL CONDITIONAL RANDOM FIELD MODEL FOR REMOTE SENSING IMAGE CLASSIFICATIONZ. Zhang0M. Y. Yang1M. Zhou2Academy of OptoElectronics, Chinese Academy of Sciences, Beijing, ChinaInstitute for Information Processing (TNT), Leibniz University Hannover, GermanyAcademy of OptoElectronics, Chinese Academy of Sciences, Beijing, ChinaFusion of remote sensing images and LiDAR data provides complimentary information for the remote sensing applications, such as object classification and recognition. In this paper, we propose a novel multi-source multi-scale hierarchical conditional random field (MSMSH-CRF) model to integrate features extracted from remote sensing images and LiDAR point cloud data for image classification. MSMSH-CRF model is then constructed to exploit the features, category compatibility of multi-scale images and the category consistency of multi-source data based on the regions. The output of the model represents the optimal results of the image classification. We have evaluated the precision and robustness of the proposed method on airborne data, which shows that the proposed method outperforms standard CRF method.http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W4/293/2015/isprsannals-II-3-W4-293-2015.pdf |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Z. Zhang M. Y. Yang M. Zhou |
spellingShingle |
Z. Zhang M. Y. Yang M. Zhou MULTI-SOURCE MULTI-SCALE HIERARCHICAL CONDITIONAL RANDOM FIELD MODEL FOR REMOTE SENSING IMAGE CLASSIFICATION ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
author_facet |
Z. Zhang M. Y. Yang M. Zhou |
author_sort |
Z. Zhang |
title |
MULTI-SOURCE MULTI-SCALE HIERARCHICAL CONDITIONAL RANDOM FIELD MODEL FOR REMOTE SENSING IMAGE CLASSIFICATION |
title_short |
MULTI-SOURCE MULTI-SCALE HIERARCHICAL CONDITIONAL RANDOM FIELD MODEL FOR REMOTE SENSING IMAGE CLASSIFICATION |
title_full |
MULTI-SOURCE MULTI-SCALE HIERARCHICAL CONDITIONAL RANDOM FIELD MODEL FOR REMOTE SENSING IMAGE CLASSIFICATION |
title_fullStr |
MULTI-SOURCE MULTI-SCALE HIERARCHICAL CONDITIONAL RANDOM FIELD MODEL FOR REMOTE SENSING IMAGE CLASSIFICATION |
title_full_unstemmed |
MULTI-SOURCE MULTI-SCALE HIERARCHICAL CONDITIONAL RANDOM FIELD MODEL FOR REMOTE SENSING IMAGE CLASSIFICATION |
title_sort |
multi-source multi-scale hierarchical conditional random field model for remote sensing image classification |
publisher |
Copernicus Publications |
series |
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
issn |
2194-9042 2194-9050 |
publishDate |
2015-03-01 |
description |
Fusion of remote sensing images and LiDAR data provides complimentary information for the remote sensing applications, such as
object classification and recognition. In this paper, we propose a novel multi-source multi-scale hierarchical conditional random field
(MSMSH-CRF) model to integrate features extracted from remote sensing images and LiDAR point cloud data for image classification.
MSMSH-CRF model is then constructed to exploit the features, category compatibility of multi-scale images and the category
consistency of multi-source data based on the regions. The output of the model represents the optimal results of the image classification.
We have evaluated the precision and robustness of the proposed method on airborne data, which shows that the proposed method
outperforms standard CRF method. |
url |
http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W4/293/2015/isprsannals-II-3-W4-293-2015.pdf |
work_keys_str_mv |
AT zzhang multisourcemultiscalehierarchicalconditionalrandomfieldmodelforremotesensingimageclassification AT myyang multisourcemultiscalehierarchicalconditionalrandomfieldmodelforremotesensingimageclassification AT mzhou multisourcemultiscalehierarchicalconditionalrandomfieldmodelforremotesensingimageclassification |
_version_ |
1725995333676171264 |