Rosa M. Pérez

A quantitative and comparative analysis of endmember extraction algorithms from hyperspectral data

Linear spectral unmixing is a commonly accepted approach to mixed-pixel classification in hyperspectral imagery. This approach involves two steps. First, to find spectrally unique signatures of pure ground components, usually known as endmembers, and, second, to express mixed pixels as linear combinations of endmember materials. Over the past years, several algorithms have been developed for autonomous and supervised endmember extraction from hyperspectral data. Due to a lack of commonly accepted data and quantitative approaches to substantiate new algorithms, available methods have not been rigorously compared by using a unified scheme. In this paper, we present a comparative study of standard endmember extraction algorithms using a custom-designed quantitative and comparative framework that involves both the spectral and spatial information. The algorithms considered in this study represent substantially different design choices. A database formed by simulated and real hyperspectral data collected by the Airborne Visible and Infrared Imaging Spectrometer (AVIRIS) is used to investigate the impact of noise, mixture complexity, and use of radiance/reflectance data on algorithm performance. The results obtained indicate that endmember selection and subsequent mixed-pixel interpretation by a linear mixture model are more successful when methods combining spatial and spectral information are applied.

Spatial/spectral endmember extraction by multidimensional morphological operations

Spectral mixture analysis provides an efficient mechanism for the interpretation and classification of remotely sensed multidimensional imagery. It aims to identify a set of reference signatures (also known as endmembers) that can be used to model the reflectance spectrum at each pixel of the original image. Thus, the modeling is carried out as a linear combination of a finite number of ground components. Although spectral mixture models have proved to be appropriate for the purpose of large hyperspectral dataset subpixel analysis, few methods are available in the literature for the extraction of appropriate endmembers in spectral unmixing. Most approaches have been designed from a spectroscopic viewpoint and, thus, tend to neglect the existing spatial correlation between pixels. This paper presents a new automated method that performs unsupervised pixel purity determination and endmember extraction from multidimensional datasets; this is achieved by using both spatial and spectral information in a combined manner. The method is based on mathematical morphology, a classic image processing technique that can be applied to the spectral domain while being able to keep its spatial characteristics. The proposed methodology is evaluated through a specifically designed framework that uses both simulated and real hyperspectral data.

Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations

This work describes sequences of extended morphological transformations for filtering and classification of high-dimensional remotely sensed hyperspectral datasets. The proposed approaches are based on the generalization of concepts from mathematical morphology theory to multichannel imagery. A new vector organization scheme is described, and fundamental morphological vector operations are defined by extension. Extended morphological transformations, characterized by simultaneously considering the spatial and spectral information contained in hyperspectral datasets, are applied to agricultural and urban classification problems where efficacy in discriminating between subtly different ground covers is required. The methods are tested using real hyperspectral imagery collected by the National Aeronautics and Space Administration Jet Propulsion Laboratory Airborne Visible-Infrared Imaging Spectrometer and the German Aerospace Agency Digital Airborne Imaging Spectrometer (DAIS 7915). Experimental results reveal that, by designing morphological filtering methods that take into account the complementary nature of spatial and spectral information in a simultaneous manner, it is possible to alleviate the problems related to each of them when taken separately.

A new approach to mixed pixel classification of hyperspectral imagery based on extended morphological profiles

Abstract This paper presents a new approach to the analysis of hyperspectral images, a new class of image data that is mainly used in remote sensing applications. The method is based on the generalization of concepts from mathematical morphology to multi-channel imagery. A new vector organization scheme is described, and fundamental morphological vector operations are defined by extension. Theoretical definitions of extended morphological operations are used in the formal definition of the concept of extended morphological profile, which is used for multi-scale analysis of hyperspectral data. This approach is particularly well suited for the analysis of image scenes where most of the pixels collected by the sensor are characterized by their mixed nature, i.e. they are formed by a combination of multiple underlying responses produced by spectrally distinct materials. Experimental results demonstrate the applicability of the proposed technique in mixed pixel analysis of simulated and real hyperspectral data collected by the NASA/Jet Propulsion Laboratory Airborne Visible/Infrared Imaging Spectrometer and the DLR Digital Airborne (DAIS 7915) and Reflective Optics System Imaging Spectrometers. The proposed method works effectively in the presence of noise and low spatial resolution. A quantitative and comparative performance study with regards to other standard hyperspectral analysis methodologies reveals that the combined utilization of spatial and spectral information in the proposed technique produces classification results which are superior to those found by using the spectral information alone.

On the use of small training sets for neural network-based characterization of mixed pixels in remotely sensed hyperspectral images

In this work, neural network-based models involved in hyperspectral image spectra separation are considered. Focus is on how to select the most highly informative samples for effectively training the neural architecture. This issue is addressed here by several new algorithms for intelligent selection of training samples: (1) a border-training algorithm (BTA) which selects training samples located in the vicinity of the hyperplanes that can optimally separate the classes; (2) a mixed-signature algorithm (MSA) which selects the most spectrally mixed pixels in the hyperspectral data as training samples; and (3) a morphological-erosion algorithm (MEA) which incorporates spatial information (via mathematical morphology concepts) to select spectrally mixed training samples located in spatially homogeneous regions. These algorithms, along with other standard techniques based on orthogonal projections and a simple Maximin-distance algorithm, are used to train a multi-layer perceptron (MLP), selected in this work as a representative neural architecture for spectral mixture analysis. Experimental results are provided using both a database of nonlinear mixed spectra with absolute ground truth and a set of real hyperspectral images, collected at different altitudes by the digital airborne imaging spectrometer (DAIS 7915) and reflective optics system imaging spectrometer (ROSIS) operating simultaneously at multiple spatial resolutions.

Joint linear/nonlinear spectral unmixing of hyperspectral image data

Many available techniques for spectral mixture analysis involve the separation of mixed pixel spectra collected by imaging spectrometers into pure component (endmember) spectra, and the estimation of abundance values for each end- member. Although linear mixing models generally provide a good abstraction of the mixing process, several naturally occurring situations exist where nonlinear models may provide the most accurate assessment of endmember abundance. In this paper, we propose a combined linear/nonlinear mixture model which makes use of linear mixture analysis to provide an initial model estimation, which is then thoroughly refined using a multi-layer neural network coupled with intelligent algorithms for automatic selection of training samples. Three different algorithms for automatic selection of training samples, such as border training algorithm (BTA), mixed signature algorithm (MSA) and mophological erosion algorithm (MEA) are developed for this purpose. The proposed model is evaluated in the context of a real application which involves the use of hyperspectral data sets, collected by the Digital Airborne (DAIS 7915) and Reflective Optics System (ROSIS) imaging spectrometers of DLR, operating simultaneously at multiple spatial resolutions.

Nonlinear mixture models for analyzing laboratory simulated-forest hyperspectral data

The interpretation of mixed pixels is a key factor in the analysis of hyperspectral imagery. A commonly used approach to mixed pixel classification has been linear spectral unmixing. However, the question of whether linear or nonlinear processes dominate spectral signatures of mixed pixels is still an unresolved matter. In this paper we describe new methodologies for inferring land cover fractions within hyperspectral scenes, using nonlinear mixture modeling techniques based on support vector machines and neural network-based techniques. A comparative analysis of these mixture estimation methods to the standard linear mixture model has been carried out using a database of laboratory simulated-forest scenes. For the simulations, canopies of both opaque and translucent trees were simulated using objects mounted on stems. Two tree densities (sparse and dense) and three background colors (dark, white and green) were considered. Hyperspectral images of these simulated scenes were acquired by the Compact Airborne Spectrographic Imager (CASI), and the areal fractions of the main constituents calculated by the SPRINT canopy model were used for comparison. Our quantitative and comparative analysis reveals that nonlinear approaches outperform linear mixture model-based approaches, particularly in the scenes with translucent trees. As a result, this investigation suggests that nonlinear mixture models are needed to account for the multiple scattering between tree crowns and background for the laboratory simulated-forest scenes used in this study.

H-COMP: a tool for quantitative and comparative analysis of endmember identification algorithms

Over the past years, several endmember extraction algorithms have been developed for spectral mixture analysis of hyperspectral data. Due to a lack of quantitative approaches to substantiate new algorithms, available methods have not been rigorously compared using a unified scheme. In this paper, we describe H-COMP, an IDL (Interactive Data Language)-based software toolkit for visualization and interactive analysis of results provided by endmember selection methods. The suitability of using H-COMP for assessment and comparison of endmember extraction algorithms is demonstrated in this work by a comparative analysis of three standard algorithms: Pixel Purity Index (PPI), N-FINDR, and Automated Morphological Endmember Extraction (AMEE). Simulated and real hyperspectral datasets, collected by the NASA/JPL Airborne Visible-Infrared Imaging Spectrometer (AVIRIS), are used to carry out a comparative effort, focused on the definition of reliable endmember quality metrics.

Spatial/Spectral analysis of hyperspectral image data

The integration of spatial and spectral responses in hyperspectral image data analysis has been identified as a desirable objective by the remote sensing community. However, most available attempts are based on the consideration of spectral information separately from spatial information, and thus the two types of information are not treated simultaneously. In this paper, we describe our background in applying joint spatial/spectral techniques for full (pure)- and mixed-pixel classification of hyperspectral image data. Most of the techniques described in this work are based on classic mathematical morphology theory, which provides a remarkable framework to achieve the desired integration. The performance of the proposed methodologies is demonstrated by comparing them to other well-known pure- and mixed-pixel classifiers, using both simulated and real hyperspectral data collected by the NASA/JPL-AVIRIS and DLR-DAIS 7915 imaging spectrometers.

A new method for target detection in hyperspectral imagery based on extended morphological profiles

Hyperspectral remote sensing increases the detectability of pixel-and subpixel-sized targets by exploiting the finer detail in the spectral signatures. In this paper, we describe a new unsupervised algorithm for the detection of both full pixel and mixed pixel targets in hyperspectral imagery. The proposed method automatically resolves targets by using extended mathematical morphology operations. The performance of the resulting detector is experimentally evaluated using simulated and real hyperspectral data collected by the NASA/Jet Propulsion Laboratory Airborne Visible/Infrared Imaging Spectrometer and the DLR Reflective Optics System Imaging Spectrometer (ROSIS).