A Novel Negative Abundance‐Oriented Hyperspectral Unmixing Algorithm

Abstract

International audienceSpectral unmixing is a popular technique for analyzing remotely sensed hyperspectral data sets with subpixel precision. Over the last few years, many algorithms have been developed for each of the main processing steps involved in spectral unmixing (SU) under the LMM assumption: 1) estimation of the number of endmembers; 2) identification of the spectral signatures of the endmembers; and 3) estimation of the abundance of endmembers in the scene. Although this general processing chain has proven to be effective for unmixing certain types of hyperspectral images, it also has some drawbacks. The first one comes from the fact that the output of each stage is the input of the following one, which favors the propagation of errors within the unmixing chain. A second problem is the huge variability of the results obtained when estimating the number of endmembers of a hyperspectral scene with different state-of-the-art algorithms, which influences the rest of the process. A third issue is the computational complexity of the whole process. To address the aforementioned issues, this paper develops a novel negative abundance-oriented SU algorithm that covers, for the first time in the literature, the main steps involved in traditional hyperspectral unmixing chains. The proposed algorithm can also be easily adapted to a scenario in which the number of endmembers is known in advance and two additional variations of the algorithm are provided to deal with high-noise scenarios and to significantly reduce its execution time, respectively. Our experimental results, conducted using both synthetic and real hyperspectral scenes, indicate that the presented method is highly competitive (in terms of both unmixing accuracy and computational performance) with regard to other SU techniques with similar requirements, while providing a fully self-contained unmixing chain without the need for any input parameters

Hyperspectral Local Intrinsic Dimensionality

“…Three non eigen-based hyperspectral ID estimators have recently been proposed. The first one, introduced in [34] as part of a Negative ABundance-Oriented (NABO) unmixing algorithm, borrows the main idea from the HySIME algorithm. Basically, it decomposes the residual error from the unconstrained unmixing into two components, a first due to noise and a second due to ID.…”

“…This technique [34] performs spectral unmixing and dimensionality estimation at the same time. It is noteworthy that this method is not eigenvalue-based.…”

An Adaptive Surrogate-Assisted Endmember Extraction Framework Based on Intelligent Optimization Algorithms for Hyperspectral Remote Sensing Images

“…where Y = [y 1 , y 2 , ..., y N ] is the hyperspectral image matrix, A = [α 1 , α 2 , ..., α N ] and N = [n 1 , n 2 , ..., n N ] represent the abundance matrix and the noise matrix, respectively. Due to physical limitations and constraints, the abundance needs to satisfy two constraints, namely the abundance sum-to-one constraint (ASC, ∑ m j=1 α j = 1) and the abundance nonnegative constraint (ANC, α j ≥ 0, j = 1, 2, ..., m) [10].…”

Nonlinear Temperature Correction Model of Spatial Material Spectrum Based on Taylor Expansion

“…And the analysis of the influence of the ambient temperature on the spectrum of the space target has not been carried out. 6,7 Additional scattering correction method 8 , mean variance correction 9 and normalization 10 are often used to analyze the characteristics of visible light. Compared with the above methods, the nonlinear temperature correction has a unique advantage in the correction of the model.…”