Tensor Block-Sparsity Based Representation for Spectral-Spatial Hyperspectral Image Classification
Recently, sparse representation has yielded successful results in hyperspectral image (HSI) classification. In the sparse representation-based classifiers (SRCs), a more discriminative representation that preserves the spectral-spatial information can be exploited by treating the HSI as a whole enti...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/8/8/636 |
| _version_ | 1818321801729540096 |
|---|---|
| author | Zhi He Jun Li Lin Liu |
| author_facet | Zhi He Jun Li Lin Liu |
| author_sort | Zhi He |
| collection | DOAJ |
| description | Recently, sparse representation has yielded successful results in hyperspectral image (HSI) classification. In the sparse representation-based classifiers (SRCs), a more discriminative representation that preserves the spectral-spatial information can be exploited by treating the HSI as a whole entity. Based on this observation, a tensor block-sparsity based representation method is proposed for spectral-spatial classification of HSI in this paper. Unlike traditional vector/matrix-based SRCs, the proposed method consists of tensor block-sparsity based dictionary learning and class-dependent block sparse representation. By naturally regarding the HSI cube as a third-order tensor, small local patches centered at the training samples are extracted from the HSI to maintain the structural information. All the patches are then partitioned into a number of groups, on which a dictionary learning model is constructed with a tensor block-sparsity constraint. A test sample is also expressed as a small local patch and the block sparse representation is then performed in a class-wise manner to take advantage of the class label information. Finally, the category of the test sample is determined by using the minimal residual. Experimental results of two real-world HSIs show that our proposed method greatly improves the classification performance of SRC. |
| first_indexed | 2024-12-13T10:46:41Z |
| format | Article |
| id | doaj.art-54490714ee3e46d1962e21ed019f7446 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-13T10:46:41Z |
| publishDate | 2016-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-54490714ee3e46d1962e21ed019f74462022-12-21T23:50:09ZengMDPI AGRemote Sensing2072-42922016-08-018863610.3390/rs8080636rs8080636Tensor Block-Sparsity Based Representation for Spectral-Spatial Hyperspectral Image ClassificationZhi He0Jun Li1Lin Liu2Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation, Center of Integrated Geographic Information Analysis, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, ChinaGuangdong Provincial Key Laboratory of Urbanization and Geo-simulation, Center of Integrated Geographic Information Analysis, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, ChinaGuangdong Provincial Key Laboratory of Urbanization and Geo-simulation, Center of Integrated Geographic Information Analysis, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, ChinaRecently, sparse representation has yielded successful results in hyperspectral image (HSI) classification. In the sparse representation-based classifiers (SRCs), a more discriminative representation that preserves the spectral-spatial information can be exploited by treating the HSI as a whole entity. Based on this observation, a tensor block-sparsity based representation method is proposed for spectral-spatial classification of HSI in this paper. Unlike traditional vector/matrix-based SRCs, the proposed method consists of tensor block-sparsity based dictionary learning and class-dependent block sparse representation. By naturally regarding the HSI cube as a third-order tensor, small local patches centered at the training samples are extracted from the HSI to maintain the structural information. All the patches are then partitioned into a number of groups, on which a dictionary learning model is constructed with a tensor block-sparsity constraint. A test sample is also expressed as a small local patch and the block sparse representation is then performed in a class-wise manner to take advantage of the class label information. Finally, the category of the test sample is determined by using the minimal residual. Experimental results of two real-world HSIs show that our proposed method greatly improves the classification performance of SRC.http://www.mdpi.com/2072-4292/8/8/636hyperspectral image (HSI)classificationtensordictionary learningsparse representation |
| spellingShingle | Zhi He Jun Li Lin Liu Tensor Block-Sparsity Based Representation for Spectral-Spatial Hyperspectral Image Classification Remote Sensing hyperspectral image (HSI) classification tensor dictionary learning sparse representation |
| title | Tensor Block-Sparsity Based Representation for Spectral-Spatial Hyperspectral Image Classification |
| title_full | Tensor Block-Sparsity Based Representation for Spectral-Spatial Hyperspectral Image Classification |
| title_fullStr | Tensor Block-Sparsity Based Representation for Spectral-Spatial Hyperspectral Image Classification |
| title_full_unstemmed | Tensor Block-Sparsity Based Representation for Spectral-Spatial Hyperspectral Image Classification |
| title_short | Tensor Block-Sparsity Based Representation for Spectral-Spatial Hyperspectral Image Classification |
| title_sort | tensor block sparsity based representation for spectral spatial hyperspectral image classification |
| topic | hyperspectral image (HSI) classification tensor dictionary learning sparse representation |
| url | http://www.mdpi.com/2072-4292/8/8/636 |
| work_keys_str_mv | AT zhihe tensorblocksparsitybasedrepresentationforspectralspatialhyperspectralimageclassification AT junli tensorblocksparsitybasedrepresentationforspectralspatialhyperspectralimageclassification AT linliu tensorblocksparsitybasedrepresentationforspectralspatialhyperspectralimageclassification |