Spectral Unmixing of Hyperspectral Remote Sensing Imagery via Preserving the Intrinsic Structure Invariant
Hyperspectral unmixing, which decomposes mixed pixels into endmembers and corresponding abundance maps of endmembers, has obtained much attention in recent decades. Most spectral unmixing algorithms based on non-negative matrix factorization (NMF) do not explore the intrinsic manifold structure of h...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/10/3528 |
| _version_ | 1818040167377666048 |
|---|---|
| author | Yang Shao Jinhui Lan Yuzhen Zhang Jinlin Zou |
| author_facet | Yang Shao Jinhui Lan Yuzhen Zhang Jinlin Zou |
| author_sort | Yang Shao |
| collection | DOAJ |
| description | Hyperspectral unmixing, which decomposes mixed pixels into endmembers and corresponding abundance maps of endmembers, has obtained much attention in recent decades. Most spectral unmixing algorithms based on non-negative matrix factorization (NMF) do not explore the intrinsic manifold structure of hyperspectral data space. Studies have proven image data is smooth along the intrinsic manifold structure. Thus, this paper explores the intrinsic manifold structure of hyperspectral data space and introduces manifold learning into NMF for spectral unmixing. Firstly, a novel projection equation is employed to model the intrinsic structure of hyperspectral image preserving spectral information and spatial information of hyperspectral image. Then, a graph regularizer which establishes a close link between hyperspectral image and abundance matrix is introduced in the proposed method to keep intrinsic structure invariant in spectral unmixing. In this way, decomposed abundance matrix is able to preserve the true abundance intrinsic structure, which leads to a more desired spectral unmixing performance. At last, the experimental results including the spectral angle distance and the root mean square error on synthetic and real hyperspectral data prove the superiority of the proposed method over the previous methods. |
| first_indexed | 2024-12-10T08:10:13Z |
| format | Article |
| id | doaj.art-754dbe8ba87d4504a83f7f957b0e2218 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-12-10T08:10:13Z |
| publishDate | 2018-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-754dbe8ba87d4504a83f7f957b0e22182022-12-22T01:56:35ZengMDPI AGSensors1424-82202018-10-011810352810.3390/s18103528s18103528Spectral Unmixing of Hyperspectral Remote Sensing Imagery via Preserving the Intrinsic Structure InvariantYang Shao0Jinhui Lan1Yuzhen Zhang2Jinlin Zou3School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaHyperspectral unmixing, which decomposes mixed pixels into endmembers and corresponding abundance maps of endmembers, has obtained much attention in recent decades. Most spectral unmixing algorithms based on non-negative matrix factorization (NMF) do not explore the intrinsic manifold structure of hyperspectral data space. Studies have proven image data is smooth along the intrinsic manifold structure. Thus, this paper explores the intrinsic manifold structure of hyperspectral data space and introduces manifold learning into NMF for spectral unmixing. Firstly, a novel projection equation is employed to model the intrinsic structure of hyperspectral image preserving spectral information and spatial information of hyperspectral image. Then, a graph regularizer which establishes a close link between hyperspectral image and abundance matrix is introduced in the proposed method to keep intrinsic structure invariant in spectral unmixing. In this way, decomposed abundance matrix is able to preserve the true abundance intrinsic structure, which leads to a more desired spectral unmixing performance. At last, the experimental results including the spectral angle distance and the root mean square error on synthetic and real hyperspectral data prove the superiority of the proposed method over the previous methods.http://www.mdpi.com/1424-8220/18/10/3528spectral unmixinghyperspectral imageryintrinsic structurelocal window |
| spellingShingle | Yang Shao Jinhui Lan Yuzhen Zhang Jinlin Zou Spectral Unmixing of Hyperspectral Remote Sensing Imagery via Preserving the Intrinsic Structure Invariant Sensors spectral unmixing hyperspectral imagery intrinsic structure local window |
| title | Spectral Unmixing of Hyperspectral Remote Sensing Imagery via Preserving the Intrinsic Structure Invariant |
| title_full | Spectral Unmixing of Hyperspectral Remote Sensing Imagery via Preserving the Intrinsic Structure Invariant |
| title_fullStr | Spectral Unmixing of Hyperspectral Remote Sensing Imagery via Preserving the Intrinsic Structure Invariant |
| title_full_unstemmed | Spectral Unmixing of Hyperspectral Remote Sensing Imagery via Preserving the Intrinsic Structure Invariant |
| title_short | Spectral Unmixing of Hyperspectral Remote Sensing Imagery via Preserving the Intrinsic Structure Invariant |
| title_sort | spectral unmixing of hyperspectral remote sensing imagery via preserving the intrinsic structure invariant |
| topic | spectral unmixing hyperspectral imagery intrinsic structure local window |
| url | http://www.mdpi.com/1424-8220/18/10/3528 |
| work_keys_str_mv | AT yangshao spectralunmixingofhyperspectralremotesensingimageryviapreservingtheintrinsicstructureinvariant AT jinhuilan spectralunmixingofhyperspectralremotesensingimageryviapreservingtheintrinsicstructureinvariant AT yuzhenzhang spectralunmixingofhyperspectralremotesensingimageryviapreservingtheintrinsicstructureinvariant AT jinlinzou spectralunmixingofhyperspectralremotesensingimageryviapreservingtheintrinsicstructureinvariant |