Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph Embedding
Many graph embedding methods are developed for dimensionality reduction (DR) of hyperspectral image (HSI), which only use spectral features to reflect a point-to-point intrinsic relation and ignore complex spatial-spectral structure in HSI. A new DR method termed spatial-spectral regularized sparse...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/9/1039 |
| _version_ | 1818971412473315328 |
|---|---|
| author | Hong Huang Meili Chen Yule Duan |
| author_facet | Hong Huang Meili Chen Yule Duan |
| author_sort | Hong Huang |
| collection | DOAJ |
| description | Many graph embedding methods are developed for dimensionality reduction (DR) of hyperspectral image (HSI), which only use spectral features to reflect a point-to-point intrinsic relation and ignore complex spatial-spectral structure in HSI. A new DR method termed spatial-spectral regularized sparse hypergraph embedding (SSRHE) is proposed for the HSI classification. SSRHE explores sparse coefficients to adaptively select neighbors for constructing the dual sparse hypergraph. Based on the spatial coherence property of HSI, a local spatial neighborhood scatter is computed to preserve local structure, and a total scatter is computed to represent the global structure of HSI. Then, an optimal discriminant projection is obtained by possessing better intraclass compactness and interclass separability, which is beneficial for classification. Experiments on Indian Pines and PaviaU hyperspectral datasets illustrated that SSRHE effectively develops a better classification performance compared with the traditional spectral DR algorithms. |
| first_indexed | 2024-12-20T14:51:58Z |
| format | Article |
| id | doaj.art-8aa0dd07e0f2483496fde76a67fc3a84 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-20T14:51:58Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8aa0dd07e0f2483496fde76a67fc3a842022-12-21T19:36:57ZengMDPI AGRemote Sensing2072-42922019-05-01119103910.3390/rs11091039rs11091039Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph EmbeddingHong Huang0Meili Chen1Yule Duan2Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing 400044, ChinaKey Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing 400044, ChinaKey Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing 400044, ChinaMany graph embedding methods are developed for dimensionality reduction (DR) of hyperspectral image (HSI), which only use spectral features to reflect a point-to-point intrinsic relation and ignore complex spatial-spectral structure in HSI. A new DR method termed spatial-spectral regularized sparse hypergraph embedding (SSRHE) is proposed for the HSI classification. SSRHE explores sparse coefficients to adaptively select neighbors for constructing the dual sparse hypergraph. Based on the spatial coherence property of HSI, a local spatial neighborhood scatter is computed to preserve local structure, and a total scatter is computed to represent the global structure of HSI. Then, an optimal discriminant projection is obtained by possessing better intraclass compactness and interclass separability, which is beneficial for classification. Experiments on Indian Pines and PaviaU hyperspectral datasets illustrated that SSRHE effectively develops a better classification performance compared with the traditional spectral DR algorithms.https://www.mdpi.com/2072-4292/11/9/1039hyperspectral imagedimensionality reductionspatial-spectral featurehypergraph embeddingsparse representation |
| spellingShingle | Hong Huang Meili Chen Yule Duan Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph Embedding Remote Sensing hyperspectral image dimensionality reduction spatial-spectral feature hypergraph embedding sparse representation |
| title | Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph Embedding |
| title_full | Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph Embedding |
| title_fullStr | Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph Embedding |
| title_full_unstemmed | Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph Embedding |
| title_short | Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph Embedding |
| title_sort | dimensionality reduction of hyperspectral image using spatial spectral regularized sparse hypergraph embedding |
| topic | hyperspectral image dimensionality reduction spatial-spectral feature hypergraph embedding sparse representation |
| url | https://www.mdpi.com/2072-4292/11/9/1039 |
| work_keys_str_mv | AT honghuang dimensionalityreductionofhyperspectralimageusingspatialspectralregularizedsparsehypergraphembedding AT meilichen dimensionalityreductionofhyperspectralimageusingspatialspectralregularizedsparsehypergraphembedding AT yuleduan dimensionalityreductionofhyperspectralimageusingspatialspectralregularizedsparsehypergraphembedding |