Endmembers In Hyperspectral Images Research Articles

Kernel sparse representation for hyperspectral unmixing based on high mutual coherence spectral library

ABSTRACTSparse regression is now a popular method for hyperspectral unmixing relying on a prior spectral library. However, it is limited by the high mutual coherence spectral library which contains high similarity atoms. In order to improve the accuracy of sparse unmixing with a high mutual coherence spectral library, a new algorithm based on kernel sparse representation unmixing model with total variation constraint is proposed in this paper. By constructing an appropriate kernel function to expand similarity measure scale, library atoms and hyperspectral data are mapped to kernel space where sparse regression algorithms are then applied. Experiments conducted with both simulated and real hyperspectral data sets indicate that the proposed algorithm effectively improves the unmixing performance when using a high mutual coherence spectral library because of its ability to precisely extract endmembers in hyperspectral images. Compared with other state-of-the-art algorithms, the proposed algorithm obtains low reconstruction errors in pixels with different mixed degree.

Improved pure pixel identification algorithms to determine the endmembers in hyperspectral images

Hyperspectral image analysis mainly concentrates on handling big satellite datasets efficiently and to identify the endmembers more accurately. This paper proposes improved pure pixel identification algorithms to identify the endmembers in hyperspectral images. In the proposed endmember extraction algorithms the skewers are generated based on the statistical parameters of the hyperspectral dataset, which implicitly changes the vertices of the convex hull. This reduces the false alarm probability of the conventional Pixel Purity Index algorithm. Moreover in the proposed Skewer based NFINDR algorithm eliminates the random initialization of the endmembers in the first step, which leads to more promising results. The running time is reduced by decreasing the floating point operations involved. Experimental results validate the effectiveness of the proposed endmember extraction algorithms in terms of improved accuracy and reduced computational complexity. My study proves the proposed algorithms were able to identify the endmembers accurately even in a noisy environment, thereby validating its effectiveness.

Independent Base Vector Representation to Address Endmember Variability in Hyperspectral Unmixing

The normal compositional model (NCM) is a well-known and powerful model in hyperspectral unmixing which represents endmembers as independent Gaussian vectors to capture endmember variability. However, the assumption of independent endmembers diminishes the model accuracy because the high degree of correlation between endmembers of a scene and identical sources of variability demonstrate that the endmembers are dependent. This paper proposes a new hyperspectral unmixing algorithm which represents endmembers using dependent Gaussian vectors to estimate abundance fractions. To overcome the higher complexity caused by dependence assumption, this algorithm introduces new independent Gaussian vectors named Base Vectors to represent different endmembers by a weighted linear combination. Also, the proposed unmixing algorithm uses maximum likelihood method to estimate weight coefficients of Base Vectors which are used to represent mixed pixel. Finally, abundance estimation can be done using the new representation for endmembers and mixed pixel. The proposed algorithm is evaluated and compared with other state-of-the-art unmixing algorithms using simulated and real hyperspectral images. Experimental results demonstrate that the proposed unmixing algorithm can unmix pixels composed of correlated endmembers in hyperspectral images in the presence of spectral variability more accurately than previous methods.

Estimating the Intrinsic Dimension of Hyperspectral Images Using a Noise-Whitened Eigengap Approach

Linear mixture models are commonly used to represent hyperspectral datacube as a linear combinations of endmember spectra. However, determining of the number of endmembers for images embedded in noise is a crucial task. This paper proposes a fully automatic approach for estimating the number of endmembers in hyperspectral images. The estimation is based on recent results of random matrix theory related to the so-called spiked population model. More precisely, we study the gap between successive eigenvalues of the sample covariance matrix constructed from high dimensional noisy samples. The resulting estimation strategy is unsupervised and robust to correlated noise. This strategy is validated on both synthetic and real images. The experimental results are very promising and show the accuracy of this algorithm with respect to state-of-the-art algorithms.

Extraction of Endmembers From Hyperspectral Images Using A Weighted Fuzzy Purified-Means Clustering Model

Hyperspectral endmembers are the spectra of pure materials that are responsible for generating the mixed pixels in hyperspectral images (HSIs). Hyperspectral endmember extraction (HEE) is essentially an inverse problem, where the unknown endmembers are inferred from the spectral measurements. Efficient extraction of endmembers in HSI relies on a well-defined generative model that captures key factors in HSI generation process, such as the clustering effect in the spatial domain and the noise heterogeneity effect in the spectral domain. This paper presents a weighted fuzzy purified-means (WFP-means) clustering model for HEE, where the endmembers are modeled as mean vectors of individual classes, and the fractional contributions of individual endmembers, called abundances, are treated as soft class membership. Accordingly, an endmember is estimated as the weighted mean of purified pixels in HSI, while the abundances are estimated as the nonnegative regression coefficients. In contrast to a mixed pixel that consists of multiple endmembers, a “purified pixel” is due to a single endmember. The introduction of the concept of “purified pixels” into the fuzzy clustering model leads to an elegant optimization scheme. Moreover, the proposed model accounts for the noise variance heterogeneity issue, which is essential for achieving unbiased abundance estimation. The proposed method is tested on both simulated and real HSI, in comparison with several other HEE methods. The results demonstrate that the proposed method compares favorably with respect to the referenced methods in terms of both endmember and abundance estimation.

An Agent-Based Artificial Bee Colony (ABC) Algorithm for Hyperspectral Image Endmember Extraction in Parallel

Endmember extraction (EE) is an important process in hyperspectral image processing, and swarm intelligence algorithms have been developed to provide effective solutions for EE. However, these algorithms have limitations in terms of their calculation efficiency. To increase the computing speed of these algorithms by fully utilizing their potential parallel nature, this paper uses the artificial bee colony (ABC) algorithm to develop a multiagent system (MAS) for extracting endmembers from hyperspectral images. In this paper, EE is described as an optimization problem that involves the simplex volume and root-mean-square error (RMSE), and the ABC algorithm is used to obtain the optimal solution to the problem. To accelerate the execution of the ABC algorithm, it is incorporated into an established MAS platform that provides the advantages of high parallel computing efficiency, flexible system architecture, and responsive fault tolerance. Artificial bees and food sources, which are the two key components of the ABC algorithm, are implemented as standalone software agents. Different agents cooperate with each other via communication and produce the optimal solution. Comparative experiments are conducted to evaluate the performance of the agent-based ABC approach. The results indicate that the proposed agent-based ABC method can effectively solve the EE problem in distributive and high-speed computing environments.

A hyperspectral image endmember extraction algorithm based on generalized morphology

Generalized morphological operator can generate less statistical bias in the output than classical morphological operator. Comprehensive utilization of spectral and spatial information of pixels, an endmember extraction algorithm based on generalized morphology is proposed. For the limitations of morphological operator in the pixel arrangement rule and replacement criteria, the reference pixel is introduced. In order to avoid the cross substitution phenomenon at the boundary of different object categories in the image, an endmember is extracted by calculating the generalized opening-closing (GOC) operator which uses the modified energy function as a distance measure. The algorithm is verified by using simulated data and real data. Experimental results show that the proposed algorithm can extract endmember automatically without prior knowledge and achieve relatively high extraction accuracy.

Estimating the Number of Endmembers in Hyperspectral Images Using the Normal Compositional Model and a Hierarchical Bayesian Algorithm

This paper studies a semi-supervised Bayesian unmixing algorithm for hyperspectral images. This algorithm is based on the normal compositional model recently introduced by Eismann and Stein. The normal compositional model assumes that each pixel of the image is modeled as a linear combination of an unknown number of pure materials, called endmembers. However, contrary to the classical linear mixing model, these endmembers are supposed to be random in order to model uncertainties regarding their knowledge. This paper proposes to estimate the mixture coefficients of the Normal Compositional Model (referred to as abundances) as well as their number using a reversible jump Bayesian algorithm. The performance of the proposed methodology is evaluated thanks to simulations conducted on synthetic and real AVIRIS images.

ICE: a statistical approach to identifying endmembers in hyperspectral images

Several of the more important endmember-finding algorithms for hyperspectral data are discussed and some of their shortcomings highlighted. A new algorithm - iterated constrained endmembers (ICE) - which attempts to address these shortcomings is introduced. An example of its use is given. There is also a discussion of the advantages and disadvantages of normalizing spectra before the application of ICE or other endmember-finding algorithms.