A New Preprocessing Technique for Fast Hyperspectral Endmember Extraction

作者：Lopez Sebastian^*; Moure Javier F; Plaza Antonio; Callico Gustavo M; Lopez Jose F; Sarmiento Roberto

来源：IEEE Geoscience and Remote Sensing Letters, 2013, 10(5): 1070-1074.

DOI：10.1109/LGRS.2012.2229689

• Endmember extraction
• hyperspectral imaging
• linear spectral unmixing
• NFINDR
• orthogonal subspace projection (OSP)
• region-based spatial preprocessing (RBSPP)
• SPP
• spatial-spectral PP (SSPP)
• vertex component analysis (VCA)

Hyperspectral image processing represents a valuable tool for remote sensing of the Earth. This fact has led to the inclusion of hyperspectral sensors in different airborne and satellite missions for Earth observation. However, one of the main drawbacks encountered when dealing with hyperspectral images is the huge amount of data to be processed, in particular, when advanced analysis techniques such as spectral unmixing are used. The main contribution of this letter is the introduction of a novel preprocessing (PP) module, called (SEPP)-P-2, which is based on the integration of spatial and spectral information. The proposed approach can be combined with existing algorithms for endmember extraction, reducing the computational complexity of those algorithms while providing similar figures of accuracy. The key idea behind (SEPP)-P-2 is to identify and select a reduced set of pixels in the hyperspectral image, so that there is no need to process a large amount of them to get accurate spectral unmixing results. Compared to previous approaches based on similar spatial and spatial-spectral PP strategies, (SEPP)-P-2 clearly outperforms their results in terms of accuracy and computation speed, as it is demonstrated with artificial and real hyperspectral images.

• 出版日期2013-9