Endmember bundles: a new approach to incorporating endmember variability into spectral mixture analysis

Bateson, C. Ann; Asner, Gregory P.; Wessman, Carol A.

doi:10.1109/36.841987

Cited by 341 publications

(162 citation statements)

References 25 publications

Supporting

Mentioning

161

Contrasting

Unclassified

Order By: Relevance

“…Model (5) is an oversimplification of reality, as it does not take into account signature variability (from pixel to pixel) due to changes in the configuration and in the composition of substances, surface contaminants, variation in the substances such as age-induced color fading due to oxidation or bleaching, uncompensated atmospheric and environmental effects, and uncompensated errors in the sensor. Signature variability has been studied and accounted for in a few unmixing algorithms (e.g., see [50]- [52]). …”

Section: A Linear Spectral Mixture Modelmentioning

confidence: 99%

Does Independent Component Analysis Play a~Role in Unmixing Hyperspectral Data?

Nascimento

Dias

2003

Pattern Recognition and Image Analysis

114

View full text Add to dashboard Cite

Abstract-Independent component analysis (ICA) has recently been proposed as a tool to unmix hyperspectral data. ICA is founded on two assumptions: 1) the observed spectrum vector is a linear mixture of the constituent spectra (endmember spectra) weighted by the correspondent abundance fractions (sources); 2) sources are statistically independent. Independent factor analysis (IFA) extends ICA to linear mixtures of independent sources immersed in noise. Concerning hyperspectral data, the first assumption is valid whenever the multiple scattering among the distinct constituent substances (endmembers) is negligible, and the surface is partitioned according to the fractional abundances. The second assumption, however, is violated, since the sum of abundance fractions associated to each pixel is constant due to physical constraints in the data acquisition process. Thus, sources cannot be statistically independent, this compromising the performance of ICA/IFA algorithms in hyperspectral unmixing. This paper studies the impact of hyperspectral source statistical dependence on ICA and IFA performances. We conclude that the accuracy of these methods tends to improve with the increase of the signature variability, of the number of endmembers, and of the signal-to-noise ratio. In any case, there are always endmembers incorrectly unmixed. We arrive to this conclusion by minimizing the mutual information of simulated and real hyperspectral mixtures. The computation of mutual information is based on fitting mixtures of Gaussians to the observed data. A method to sort ICA and IFA estimates in terms of the likelihood of being correctly unmixed is proposed.Index Terms-Independent component analysis (ICA), independent factor analysis (IFA), mixture of Gaussians, unmixing hyperspectral data.

show abstract

Section: A Linear Spectral Mixture Modelmentioning

confidence: 99%

Does Independent Component Analysis Play a~Role in Unmixing Hyperspectral Data?

Nascimento

Dias

2003

Pattern Recognition and Image Analysis

114

View full text Add to dashboard Cite

show abstract

“…The inclusion of the covariance structure of endmembers in spectral unmixing methods can improve classification accuracy when species display similar spectra [60,61]. BSVM uses the full spectral variability of the focal species to generate decision values and to create complex boundaries between classes.…”

Section: Discussionmentioning

confidence: 99%

Determining Subcanopy Psidium cattleianum Invasion in Hawaiian Forests Using Imaging Spectroscopy

et al. 2016

View full text Add to dashboard Cite

High-resolution airborne imaging spectroscopy represents a promising avenue for mapping the spread of invasive tree species through native forests, but for this technology to be useful to forest managers there are two main technical challenges that must be addressed: (1) mapping a single focal species amongst a diverse array of other tree species; and (2) detecting early outbreaks of invasive plant species that are often hidden beneath the forest canopy. To address these challenges, we investigated the performance of two single-class classification frameworks-Biased Support Vector Machine (BSVM) and Mixture Tuned Matched Filtering (MTMF)-to estimate the degree of Psidium cattleianum incidence over a range of forest vertical strata (relative canopy density). We demonstrate that both BSVM and MTMF have the ability to detect relative canopy density of a single focal plant species in a vertically stratified forest, but they differ in the degree of user input required. Our results suggest BSVM as a promising method to disentangle spectrally-mixed classifications, as this approach generates decision values from a similarity function (kernel), which optimizes complex comparisons between classes using a dynamic machine learning process.

show abstract

“…The minimum volume transform (MVT) algorithm [16] determines the simplex of a minimal volume that contains the data. The method presented in [17] is also of MVT type, but by introducing the notion of bundles, it takes into account the endmember variability that is usually present in hyperspectral mixtures.…”

Section: Related Workmentioning

confidence: 99%

Two Linear Unmixing Algorithms to Recognize Targets Using Supervised Classification and Orthogonal Rotation in Airborne Hyperspectral Images

Averbuch

Zheludev

2012

Remote Sensing

View full text Add to dashboard Cite

The goal of the paper is to detect pixels that contain targets of known spectra. The target can be present in a sub-or above pixel. Pixels without targets are classified as background pixels. Each pixel is treated via the content of its neighborhood. A pixel whose spectrum is different from its neighborhood is classified as a "suspicious point". In each suspicious point there is a mix of target(s) and background. The main objective in a supervised detection (also called "target detection") is to search for a specific given spectral material (target) in hyperspectral imaging (HSI) where the spectral signature of the target is known a priori from laboratory measurements. In addition, the fractional abundance of the target is computed. To achieve this we present two linear unmixing algorithms that recognize targets with known (given) spectral signatures. The CLUN is based on automatic feature extraction from the target's spectrum. These features separate the target from the background. The ROTU algorithm is based on embedding the spectra space into a special space by random orthogonal transformation and on the statistical properties of the embedded result. Experimental results demonstrate that the targets' locations were extracted correctly and these algorithms are robust and efficient.

show abstract

Endmember bundles: a new approach to incorporating endmember variability into spectral mixture analysis

Cited by 341 publications

References 25 publications

Does Independent Component Analysis Play a~Role in Unmixing Hyperspectral Data?

Does Independent Component Analysis Play a~Role in Unmixing Hyperspectral Data?

Determining Subcanopy Psidium cattleianum Invasion in Hawaiian Forests Using Imaging Spectroscopy

Two Linear Unmixing Algorithms to Recognize Targets Using Supervised Classification and Orthogonal Rotation in Airborne Hyperspectral Images

Contact Info

Product

Resources

About