Unsupervised hyperspectral band selection by combination of unmixing and sequential clustering techniques
| Autor: | Khelifa Djerriri, Mohammed Amine Bouhlala, Sarra Ikram Benabadji, Moussa Sofiane Karoui, Nezha Farhi, Issam Boukerch |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Atmospheric Science
010504 meteorology & atmospheric sciences Computer science 0211 other engineering and technologies 02 engineering and technology 01 natural sciences linear spectral unmixing lcsh:Oceanography Band selection lcsh:GC1-1581 Computers in Earth Sciences Cluster analysis 021101 geological & geomatics engineering 0105 earth and related environmental sciences General Environmental Science dimensionality reduction unsupervised band selection business.industry Applied Mathematics Dimensionality reduction lcsh:QE1-996.5 Hyperspectral imaging Pattern recognition Spectral bands sequential clustering lcsh:Geology hyperspectral imagery Key (cryptography) Artificial intelligence business |
| Zdroj: | European Journal of Remote Sensing, Vol 52, Iss 1, Pp 30-39 (2019) |
| ISSN: | 2279-7254 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|