Spectral-Locational-Spatial Manifold Learning for Hyperspectral Images Dimensionality Reduction
Dimensionality reduction (DR) plays an important role in hyperspectral image (HSI) classification. Unsupervised DR (uDR) is more practical due to the difficulty of obtaining class labels and their scarcity for HSIs. However, many existing uDR algorithms lack the comprehensive exploration of spectral...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/14/2752 |
| _version_ | 1797526116708122624 |
|---|---|
| author | Na Li Deyun Zhou Jiao Shi Tao Wu Maoguo Gong |
| author_facet | Na Li Deyun Zhou Jiao Shi Tao Wu Maoguo Gong |
| author_sort | Na Li |
| collection | DOAJ |
| description | Dimensionality reduction (DR) plays an important role in hyperspectral image (HSI) classification. Unsupervised DR (uDR) is more practical due to the difficulty of obtaining class labels and their scarcity for HSIs. However, many existing uDR algorithms lack the comprehensive exploration of spectral-locational-spatial (SLS) information, which is of great significance for uDR in view of the complex intrinsic structure in HSIs. To address this issue, two uDR methods called SLS structure preserving projection (SLSSPP) and SLS reconstruction preserving embedding (SLSRPE) are proposed. Firstly, to facilitate the extraction of SLS information, a weighted spectral-locational (wSL) datum is generated to break the locality of spatial information extraction. Then, a new SLS distance (SLSD) excavating the SLS relationships among samples is designed to select effective SLS neighbors. In SLSSPP, a new uDR model that includes a SLS adjacency graph based on SLSD and a cluster centroid adjacency graph based on wSL data is proposed, which compresses intraclass samples and approximately separates interclass samples in an unsupervised manner. Meanwhile, in SLSRPE, for preserving the SLS relationship among target pixels and their nearest neighbors, a new SLS reconstruction weight was defined to obtain the more discriminative projection. Experimental results on the Indian Pines, Pavia University and Salinas datasets demonstrate that, through KNN and SVM classifiers with different classification conditions, the classification accuracies of SLSSPP and SLSRPE are approximately <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.88</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.15</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.51</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.30</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.31</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.41</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher than that of the state-of-the-art DR algorithms. |
| first_indexed | 2024-03-10T09:24:40Z |
| format | Article |
| id | doaj.art-5a6b4d01614741cc9727914063d9bbe4 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T09:24:40Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5a6b4d01614741cc9727914063d9bbe42023-11-22T04:51:53ZengMDPI AGRemote Sensing2072-42922021-07-011314275210.3390/rs13142752Spectral-Locational-Spatial Manifold Learning for Hyperspectral Images Dimensionality ReductionNa Li0Deyun Zhou1Jiao Shi2Tao Wu3Maoguo Gong4School of Electronics and Information, Northwestern Polytechnical University, 127 West Youyi Road, Xi’an 710072, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, 127 West Youyi Road, Xi’an 710072, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, 127 West Youyi Road, Xi’an 710072, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, 127 West Youyi Road, Xi’an 710072, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi’an 710071, ChinaDimensionality reduction (DR) plays an important role in hyperspectral image (HSI) classification. Unsupervised DR (uDR) is more practical due to the difficulty of obtaining class labels and their scarcity for HSIs. However, many existing uDR algorithms lack the comprehensive exploration of spectral-locational-spatial (SLS) information, which is of great significance for uDR in view of the complex intrinsic structure in HSIs. To address this issue, two uDR methods called SLS structure preserving projection (SLSSPP) and SLS reconstruction preserving embedding (SLSRPE) are proposed. Firstly, to facilitate the extraction of SLS information, a weighted spectral-locational (wSL) datum is generated to break the locality of spatial information extraction. Then, a new SLS distance (SLSD) excavating the SLS relationships among samples is designed to select effective SLS neighbors. In SLSSPP, a new uDR model that includes a SLS adjacency graph based on SLSD and a cluster centroid adjacency graph based on wSL data is proposed, which compresses intraclass samples and approximately separates interclass samples in an unsupervised manner. Meanwhile, in SLSRPE, for preserving the SLS relationship among target pixels and their nearest neighbors, a new SLS reconstruction weight was defined to obtain the more discriminative projection. Experimental results on the Indian Pines, Pavia University and Salinas datasets demonstrate that, through KNN and SVM classifiers with different classification conditions, the classification accuracies of SLSSPP and SLSRPE are approximately <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.88</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.15</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.51</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.30</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.31</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.41</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher than that of the state-of-the-art DR algorithms.https://www.mdpi.com/2072-4292/13/14/2752dimensionality reductionhyperspectral imagesmanifold learningclassificationspectral-locational-spatial |
| spellingShingle | Na Li Deyun Zhou Jiao Shi Tao Wu Maoguo Gong Spectral-Locational-Spatial Manifold Learning for Hyperspectral Images Dimensionality Reduction Remote Sensing dimensionality reduction hyperspectral images manifold learning classification spectral-locational-spatial |
| title | Spectral-Locational-Spatial Manifold Learning for Hyperspectral Images Dimensionality Reduction |
| title_full | Spectral-Locational-Spatial Manifold Learning for Hyperspectral Images Dimensionality Reduction |
| title_fullStr | Spectral-Locational-Spatial Manifold Learning for Hyperspectral Images Dimensionality Reduction |
| title_full_unstemmed | Spectral-Locational-Spatial Manifold Learning for Hyperspectral Images Dimensionality Reduction |
| title_short | Spectral-Locational-Spatial Manifold Learning for Hyperspectral Images Dimensionality Reduction |
| title_sort | spectral locational spatial manifold learning for hyperspectral images dimensionality reduction |
| topic | dimensionality reduction hyperspectral images manifold learning classification spectral-locational-spatial |
| url | https://www.mdpi.com/2072-4292/13/14/2752 |
| work_keys_str_mv | AT nali spectrallocationalspatialmanifoldlearningforhyperspectralimagesdimensionalityreduction AT deyunzhou spectrallocationalspatialmanifoldlearningforhyperspectralimagesdimensionalityreduction AT jiaoshi spectrallocationalspatialmanifoldlearningforhyperspectralimagesdimensionalityreduction AT taowu spectrallocationalspatialmanifoldlearningforhyperspectralimagesdimensionalityreduction AT maoguogong spectrallocationalspatialmanifoldlearningforhyperspectralimagesdimensionalityreduction |