Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands
Spectral-spatial classification for hyperspectral imagery has been receiving much attention, since the detailed spectral and rich spatial information of hyperspectral images can be fully exploited to improve the classification accuracy. However, when the original hyperspectral images have very noisy...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9064549/ |
| _version_ | 1819150160261808128 |
|---|---|
| author | Ji Zhao Suzheng Tian Christian Geis Lizhe Wang Yanfei Zhong Hannes Taubenbock |
| author_facet | Ji Zhao Suzheng Tian Christian Geis Lizhe Wang Yanfei Zhong Hannes Taubenbock |
| author_sort | Ji Zhao |
| collection | DOAJ |
| description | Spectral-spatial classification for hyperspectral imagery has been receiving much attention, since the detailed spectral and rich spatial information of hyperspectral images can be fully exploited to improve the classification accuracy. However, when the original hyperspectral images have very noisy bands, these bands may have an unfavorable impact on the classification, and are often discarded in advance based on expert knowledge. In this study, a spectral-spatial conditional random field classification algorithm integrating band selection (CRFBS) is developed for hyperspectral imagery with severe noise bands. The proposed algorithm integrates band selection based on the relative utility of the spectral bands for classification. Consequently, negative effects of severe noise bands are eliminated and the need for high-quality image data is substantially reduced. In addition, the CRFBS algorithm makes comprehensive use of both the spectral and the spatial cues to improve the classification performance. The spectral cues are formulated by integrating the support vector machine and random forest algorithms to improve the spectral discriminative ability in the unary potentials, and the spatial information are modeled to consider the interactions between pixels in pairwise potentials. The experiments using different airborne and UAV-borne hyperspectral data verified the effectiveness of the CRFBS method. The CRFBS algorithm can achieve accurate interpretation of the various classification categories and a more than 3% improvement in classification accuracy, compared with the method using the original hyperspectral image with severe noise bands. |
| first_indexed | 2024-12-22T14:13:05Z |
| format | Article |
| id | doaj.art-d06484415db1455dbc1a5a2f3bbc7e08 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-22T14:13:05Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-d06484415db1455dbc1a5a2f3bbc7e082022-12-21T18:23:10ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01131597160910.1109/JSTARS.2020.29845689064549Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise BandsJi Zhao0https://orcid.org/0000-0001-9039-2789Suzheng Tian1Christian Geis2https://orcid.org/0000-0002-7961-8553Lizhe Wang3https://orcid.org/0000-0003-2766-0845Yanfei Zhong4https://orcid.org/0000-0001-9446-5850Hannes Taubenbock5https://orcid.org/0000-0003-4360-9126School of Computer Science, China University of Geosciences, Wuhan, ChinaSchool of Computer Science, China University of Geosciences, Wuhan, ChinaGerman Aerospace Center (DLR), German Remote Sensing Data Center (DFD), Oberpfaffenhofen, GermanySchool of Computer Science, China University of Geosciences, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaGerman Aerospace Center (DLR), German Remote Sensing Data Center (DFD), Oberpfaffenhofen, GermanySpectral-spatial classification for hyperspectral imagery has been receiving much attention, since the detailed spectral and rich spatial information of hyperspectral images can be fully exploited to improve the classification accuracy. However, when the original hyperspectral images have very noisy bands, these bands may have an unfavorable impact on the classification, and are often discarded in advance based on expert knowledge. In this study, a spectral-spatial conditional random field classification algorithm integrating band selection (CRFBS) is developed for hyperspectral imagery with severe noise bands. The proposed algorithm integrates band selection based on the relative utility of the spectral bands for classification. Consequently, negative effects of severe noise bands are eliminated and the need for high-quality image data is substantially reduced. In addition, the CRFBS algorithm makes comprehensive use of both the spectral and the spatial cues to improve the classification performance. The spectral cues are formulated by integrating the support vector machine and random forest algorithms to improve the spectral discriminative ability in the unary potentials, and the spatial information are modeled to consider the interactions between pixels in pairwise potentials. The experiments using different airborne and UAV-borne hyperspectral data verified the effectiveness of the CRFBS method. The CRFBS algorithm can achieve accurate interpretation of the various classification categories and a more than 3% improvement in classification accuracy, compared with the method using the original hyperspectral image with severe noise bands.https://ieeexplore.ieee.org/document/9064549/Conditional random fieldshyperspectral imageimage classificationrandom forestspectral-spatial classification |
| spellingShingle | Ji Zhao Suzheng Tian Christian Geis Lizhe Wang Yanfei Zhong Hannes Taubenbock Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Conditional random fields hyperspectral image image classification random forest spectral-spatial classification |
| title | Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands |
| title_full | Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands |
| title_fullStr | Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands |
| title_full_unstemmed | Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands |
| title_short | Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands |
| title_sort | spectral spatial classification integrating band selection for hyperspectral imagery with severe noise bands |
| topic | Conditional random fields hyperspectral image image classification random forest spectral-spatial classification |
| url | https://ieeexplore.ieee.org/document/9064549/ |
| work_keys_str_mv | AT jizhao spectralspatialclassificationintegratingbandselectionforhyperspectralimagerywithseverenoisebands AT suzhengtian spectralspatialclassificationintegratingbandselectionforhyperspectralimagerywithseverenoisebands AT christiangeis spectralspatialclassificationintegratingbandselectionforhyperspectralimagerywithseverenoisebands AT lizhewang spectralspatialclassificationintegratingbandselectionforhyperspectralimagerywithseverenoisebands AT yanfeizhong spectralspatialclassificationintegratingbandselectionforhyperspectralimagerywithseverenoisebands AT hannestaubenbock spectralspatialclassificationintegratingbandselectionforhyperspectralimagerywithseverenoisebands |