Unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniques
Selecting the decisive spectral bands is a key issue in unsupervised hyperspectral band selection techniques. These methods are the most popular ways for dimensionality reduction of original data. A compact data representation without compromising the physical information and optimizing the separati...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2019-01-01
|
| Series: | European Journal of Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/22797254.2018.1549511 |
| _version_ | 1818926407098564608 |
|---|---|
| author | Sarra Ikram Benabadji Moussa Sofiane Karoui Khelifa Djerriri Issam Boukerch Nezha Farhi Mohammed Amine Bouhlala |
| author_facet | Sarra Ikram Benabadji Moussa Sofiane Karoui Khelifa Djerriri Issam Boukerch Nezha Farhi Mohammed Amine Bouhlala |
| author_sort | Sarra Ikram Benabadji |
| collection | DOAJ |
| description | Selecting the decisive spectral bands is a key issue in unsupervised hyperspectral band selection techniques. These methods are the most popular ways for dimensionality reduction of original data. A compact data representation without compromising the physical information and optimizing the separation between different materials are the main objectives of such selection processes. In this work, a hyperspectral band selection approach is proposed based on linear spectral unmixing and sequential clustering techniques. The use of these two specific techniques constitutes the main novelty of this investigation. The proposed approach operates in different successive steps. It starts with extracting material spectra contained in the considered data using an unmixing method. Then, the variance of extracted spectra samples is calculated at each wavelength, which results in a variances vector. This one is segmented into a fixed number of clusters using a sequential clustering strategy. Finally, only one spectral band is selected for each segment. This band corresponds to the wavelength at which a maximum variance value is obtained. Experiments on three real hyperspectral data demonstrate the superiority of the proposed approach in comparison with four methods from the literature. |
| first_indexed | 2024-12-20T02:56:37Z |
| format | Article |
| id | doaj.art-cf49bd3d63a3443c96fda0d7f0972e18 |
| institution | Directory Open Access Journal |
| issn | 2279-7254 |
| language | English |
| last_indexed | 2024-12-20T02:56:37Z |
| publishDate | 2019-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | European Journal of Remote Sensing |
| spelling | doaj.art-cf49bd3d63a3443c96fda0d7f0972e182022-12-21T19:55:54ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542019-01-01521303910.1080/22797254.2018.15495111549511Unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniquesSarra Ikram Benabadji0Moussa Sofiane Karoui1Khelifa Djerriri2Issam Boukerch3Nezha Farhi4Mohammed Amine Bouhlala5Centre des Techniques SpatialesCentre des Techniques SpatialesCentre des Techniques SpatialesCentre des Techniques SpatialesCentre des Techniques SpatialesCentre des Techniques SpatialesSelecting the decisive spectral bands is a key issue in unsupervised hyperspectral band selection techniques. These methods are the most popular ways for dimensionality reduction of original data. A compact data representation without compromising the physical information and optimizing the separation between different materials are the main objectives of such selection processes. In this work, a hyperspectral band selection approach is proposed based on linear spectral unmixing and sequential clustering techniques. The use of these two specific techniques constitutes the main novelty of this investigation. The proposed approach operates in different successive steps. It starts with extracting material spectra contained in the considered data using an unmixing method. Then, the variance of extracted spectra samples is calculated at each wavelength, which results in a variances vector. This one is segmented into a fixed number of clusters using a sequential clustering strategy. Finally, only one spectral band is selected for each segment. This band corresponds to the wavelength at which a maximum variance value is obtained. Experiments on three real hyperspectral data demonstrate the superiority of the proposed approach in comparison with four methods from the literature.http://dx.doi.org/10.1080/22797254.2018.1549511hyperspectral imagerydimensionality reductionunsupervised band selectionlinear spectral unmixingsequential clustering |
| spellingShingle | Sarra Ikram Benabadji Moussa Sofiane Karoui Khelifa Djerriri Issam Boukerch Nezha Farhi Mohammed Amine Bouhlala Unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniques European Journal of Remote Sensing hyperspectral imagery dimensionality reduction unsupervised band selection linear spectral unmixing sequential clustering |
| title | Unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniques |
| title_full | Unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniques |
| title_fullStr | Unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniques |
| title_full_unstemmed | Unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniques |
| title_short | Unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniques |
| title_sort | unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniques |
| topic | hyperspectral imagery dimensionality reduction unsupervised band selection linear spectral unmixing sequential clustering |
| url | http://dx.doi.org/10.1080/22797254.2018.1549511 |
| work_keys_str_mv | AT sarraikrambenabadji unsupervisedhyperspectralbandselectionbycombinationofunmixingandsequentialclusteringtechniques AT moussasofianekaroui unsupervisedhyperspectralbandselectionbycombinationofunmixingandsequentialclusteringtechniques AT khelifadjerriri unsupervisedhyperspectralbandselectionbycombinationofunmixingandsequentialclusteringtechniques AT issamboukerch unsupervisedhyperspectralbandselectionbycombinationofunmixingandsequentialclusteringtechniques AT nezhafarhi unsupervisedhyperspectralbandselectionbycombinationofunmixingandsequentialclusteringtechniques AT mohammedaminebouhlala unsupervisedhyperspectralbandselectionbycombinationofunmixingandsequentialclusteringtechniques |