Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral Image
Low-rank representation with hypergraph regularization has achieved great success in hyperspectral imagery, which can explore global structure, and further incorporate local information. Existing hypergraph learning methods only construct the hypergraph by a fixed similarity matrix or are adaptively...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/7/1372 |
| _version_ | 1827696095697829888 |
|---|---|
| author | Jinhuan Xu Liang Xiao Jingxiang Yang |
| author_facet | Jinhuan Xu Liang Xiao Jingxiang Yang |
| author_sort | Jinhuan Xu |
| collection | DOAJ |
| description | Low-rank representation with hypergraph regularization has achieved great success in hyperspectral imagery, which can explore global structure, and further incorporate local information. Existing hypergraph learning methods only construct the hypergraph by a fixed similarity matrix or are adaptively optimal in original feature space; they do not update the hypergraph in subspace-dimensionality. In addition, the clustering performance obtained by the existing k-means-based clustering methods is unstable as the k-means method is sensitive to the initialization of the cluster centers. In order to address these issues, we propose a novel unified low-rank subspace clustering method with dynamic hypergraph for hyperspectral images (HSIs). In our method, the hypergraph is adaptively learned from the low-rank subspace feature, which can capture a more complex manifold structure effectively. In addition, we introduce a rotation matrix to simultaneously learn continuous and discrete clustering labels without any relaxing information loss. The unified model jointly learns the hypergraph and the discrete clustering labels, in which the subspace feature is adaptively learned by considering the optimal dynamic hypergraph with the self-taught property. The experimental results on real HSIs show that the proposed methods can achieve better performance compared to eight state-of-the-art clustering methods. |
| first_indexed | 2024-03-10T12:39:05Z |
| format | Article |
| id | doaj.art-d7d7943e22b5422abc46fee9c2664b0b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T12:39:05Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d7d7943e22b5422abc46fee9c2664b0b2023-11-21T14:02:16ZengMDPI AGRemote Sensing2072-42922021-04-01137137210.3390/rs13071372Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral ImageJinhuan Xu0Liang Xiao1Jingxiang Yang2School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaLow-rank representation with hypergraph regularization has achieved great success in hyperspectral imagery, which can explore global structure, and further incorporate local information. Existing hypergraph learning methods only construct the hypergraph by a fixed similarity matrix or are adaptively optimal in original feature space; they do not update the hypergraph in subspace-dimensionality. In addition, the clustering performance obtained by the existing k-means-based clustering methods is unstable as the k-means method is sensitive to the initialization of the cluster centers. In order to address these issues, we propose a novel unified low-rank subspace clustering method with dynamic hypergraph for hyperspectral images (HSIs). In our method, the hypergraph is adaptively learned from the low-rank subspace feature, which can capture a more complex manifold structure effectively. In addition, we introduce a rotation matrix to simultaneously learn continuous and discrete clustering labels without any relaxing information loss. The unified model jointly learns the hypergraph and the discrete clustering labels, in which the subspace feature is adaptively learned by considering the optimal dynamic hypergraph with the self-taught property. The experimental results on real HSIs show that the proposed methods can achieve better performance compared to eight state-of-the-art clustering methods.https://www.mdpi.com/2072-4292/13/7/1372hyperspectral imageslow-rank subspace clusteringhypergraph learningdiscrete label learning |
| spellingShingle | Jinhuan Xu Liang Xiao Jingxiang Yang Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral Image Remote Sensing hyperspectral images low-rank subspace clustering hypergraph learning discrete label learning |
| title | Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral Image |
| title_full | Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral Image |
| title_fullStr | Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral Image |
| title_full_unstemmed | Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral Image |
| title_short | Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral Image |
| title_sort | unified low rank subspace clustering with dynamic hypergraph for hyperspectral image |
| topic | hyperspectral images low-rank subspace clustering hypergraph learning discrete label learning |
| url | https://www.mdpi.com/2072-4292/13/7/1372 |
| work_keys_str_mv | AT jinhuanxu unifiedlowranksubspaceclusteringwithdynamichypergraphforhyperspectralimage AT liangxiao unifiedlowranksubspaceclusteringwithdynamichypergraphforhyperspectralimage AT jingxiangyang unifiedlowranksubspaceclusteringwithdynamichypergraphforhyperspectralimage |