<title>Automated identification of endmembers from hyperspectral data using mathematical morphology</title>

Abstract

One of the most widely used approaches to analyze hyperspectral data is pixel unmixing, which relies on the identification of the purest spectra from the data cube. Once these elements, known as "endmembers", are extracted, several methods can be used to map their spatial distributions, associations and abundances. A large variety of methodologies have been recently proposed with the purpose of extracting endmembers from hyperspectral data. Nevertheless, most of them only rely on the spectral response; spatial information has not been fully exploited yet, specially in unsupervised classification. The integration of both spatial and spectral information is becoming more relevant as the sensors tend to increase their spatial/spectral resolution. Mathematical morphology is a non-linear image analysis and pattern recognition technique that has proved to be especially well suited to segment images with irregular and complex shapes, but has rarely been applied to the classification/segmentation of multivariate remote sensing data. In this paper we propose a completely automated method, based on mathematical morphology, which allows us to integrate spectral and spatial information in the analysis of hyperspectral images. The accuracy of the proposed algorithm is tested by its application to real hyperspectral data, and the results provided are compared to those found using other existing endmember extraction algorithms.

Spatial/spectral endmember extraction by multidimensional morphological operations

“…In this case, the kernel size increases exponentially, which results in an exponential complexity ( in asymptotical notation). We have tested some variations of the previous implementation in order to reduce the computational complexity of the proposed approach, and a constrained implementation through cascade dilation operations and nonoverlapping kernel sizes [43] proved to be considerably faster than the previous approach. The constraints imposed result in a computational complexity ( in asymptotical notation).…”

Aerosol mapping over land with imaging spectroscopy using spectral autocorrelation

“…In order to circumvent the need for a priori endmember choice from a region-specific spectral selection, a number of methods for automated endmember determination has been developed (Tompkins et al 1997, Winter 1999. The algorithm by Plaza et al (2001) appears particularly suited for AVIRIS data. Inclusion of automated endmember determination would represent an elegant extension for the ARIA method, completely removing the need for a priori assumptions on endmember spectra.…”

Geospatial Data Processing Characteristics for Environmental Monitoring Tasks

“…Even the most modern satellite images will not allow to obtain the necessary information without the fast and reliable decryption methods found in most modern specialized software products. Techniques for automated decoding of images developed by a number of international research institutes and research institutes of Ukraine, including classification, contouring and recognition of images of topographic objects [9,10,11,12], allow to maximize the efficiency of decryption, in comparison with traditional non-automated methods. However, the developers of these techniques emphasize that the presence of a number of interactive processes, such as contouring, searching for reference information, classification of images by texture and brightness characteristics, significantly reduces labor productivity during decryption.…”