A Novel Spectral Unmixing Method Incorporating Spectral Variability Within Endmember Classes

Uezato, Tatsumi; Murphy, Richard J.; Melkumyan, Arman; Chlingaryan, Anna

doi:10.1109/tgrs.2015.2506168

Cited by 36 publications

(33 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Spectral unmixing is used in a wide range of applications including crop/vegetation classification, disaster monitoring, surveillance, planetary exploration, food industry, fire and chemical spread detection and wild animal tracking [1]. Endmembers play an important role in exploring spectral information of a hyperspectral image [2,3] the extraction of endmembers is the first and most crucial step in any image analysis which is the process of obtaining pure signatures of different features present in an image [1,4,5]. SU often requires the definition of the mixing model underlying the observations as presented on the data.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Spectral Unmixing: Using Artificial Neural Networks for Linear/Non-Linear Switching

et al. 2017

View full text Add to dashboard Cite

Spectral unmixing is a key process in identifying spectral signature of materials and quantifying their spatial distribution over an image. The linear model is expected to provide acceptable results when two assumptions are satisfied: (1) The mixing process should occur at macroscopic level and (2) Photons must interact with single material before reaching the sensor. However, these assumptions do not always hold and more complex nonlinear models are required. This study proposes a new hybrid method for switching between linear and nonlinear spectral unmixing of hyperspectral data based on artificial neural networks. The neural networks was trained with parameters within a window of the pixel under consideration. These parameters are computed to represent the diversity of the neighboring pixels and are based on the Spectral Angular Distance, Covariance and a non linearity parameter. The endmembers were extracted using Vertex Component Analysis while the abundances were estimated using the method identified by the neural networks (Vertex Component Analysis, Fully Constraint Least Square Method, Polynomial Post Nonlinear Mixing Model or Generalized Bilinear Model). Results show that the hybrid method performs better than each of the individual techniques with high overall accuracy, while the abundance estimation error is significantly lower than that obtained using the individual methods. Experiments on both synthetic dataset and real hyperspectral images demonstrated that the proposed hybrid switch method is efficient for solving spectral unmixing of hyperspectral images as compared to individual algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid Spectral Unmixing: Using Artificial Neural Networks for Linear/Non-Linear Switching

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Multiple endmember spectral mixture analysis (MESMA) [14] allows the variability of the endmember spectrum representative of each class and a varying number of endmember classes present within each pixel. Although MESMA has been widely used for a variety of applications [14], [25], it owns several major limitations: i) it is highly computationally expensive because MESMA needs to test a large number of combinations of endmember spectra [26], ii) MESMA tends to select an overestimated number of endmember classes because it uses the reconstruction error to select the appropriate combination of endmember spectra [27] and iii) the performance of MESMA may significantly decrease when endmember spectra (or bundles) within each class do not completely represent the spectral variability [19].…”

Section: B Linear Mixing Models Incorporating Endmember Bundlesmentioning

confidence: 99%

“…where 1 N k ∈ R N k ×1 is a column vector of ones and 0 N k ∈ R N k ×1 represent a N k -dimensional vector whose components are zeros. While these two steps are conducted separately in [15], [16], they can be also considered jointly within a multi-task Gaussian process framework [17], [19]. Even if these methods have been shown to be effective, a large number of endmember spectra within each class may be redundant.…”

Section: B Linear Mixing Models Incorporating Endmember Bundlesmentioning

confidence: 99%

“…[14]) are known to be computationally expensive, more efficient methods have been recently developed and have shown great potential [15]- [18]. However, as pointed out in [19], it is unlikely that the endmember bundles completely represent endmember variability present in an image. Such incomplete endmember bundles may lead to poor estimates of abundances.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral Unmixing With Spectral Variability Using Adaptive Bundles and Double Sparsity

Uezato

Fauvel

Dobigeon

2019

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

Spectral variability is one of the major issue when conducting hyperspectral unmixing. Within a given image composed of some elementary materials (herein referred to as endmember classes), the spectral signature characterizing these classes may spatially vary due to intrinsic component fluctuations or external factors (illumination). These redundant multiple endmember spectra within each class adversely affect the performance of unmixing methods. This paper proposes a mixing model that explicitly incorporates a hierarchical structure of redundant multiple spectra representing each class. The proposed method is designed to promote sparsity on the selection of both spectra and classes within each pixel.The resulting unmixing algorithm is able to adaptively recover several bundles of endmember spectra associated with each class and robustly estimate abundances. In addition, its flexibility allows a variable number of classes to be present within each pixel of the hyperspectral image to be unmixed. The proposed method is compared with other state-of-the-art unmixing methods that incorporate sparsity using both simulated and real hyperspectral data. The results show that the proposed method can successfully determine the variable number of classes present within each class and estimate the corresponding class abundances. Part of this work has been funded by EU FP7 through the ERANETMED JC-WATER program, MapInvPlnt Project ANR-15-NMED-0002-02 and by the MUESLI IDEX ATS project, Toulouse INP. T. Uezato and N. Dobigeon are with

show abstract

“…However, these strategies exclusively relying on the hyperspectral image to be unmixed or associated derived products may not be suitable. Indeed, the hyperspectral image may be greatly affected by variations in illumination [22]- [24], leading to unreliable weighing function. Another issue results from the fact that some materials (e.g., road or roof) show similar spectral shapes [25].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Unmixing With LiDAR Data-Aided Spatial Regularization

Uezato

Fauvel²,

Dobigeon

2018

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

Spectral unmixing methods incorporating spatial regularizations have demonstrated increasing interest. Although spatial regularizers which promote smoothness of the abundance maps have been widely used, they may overly smooth these maps and, in particular, may not preserve edges present in the hyperspectral image. Existing unmixing methods usually ignore these edge structures or use edge information derived from the hyperspectral image itself. However, this information may be affected by large amounts of noise or variations in illumination, leading to erroneous spatial information incorporated into the unmixing procedure. This paper proposes a simple, yet powerful, spectral unmixing framework which incorporates external data (i.e. LiDAR data). The LiDAR measurements can be easily exploited to adjust standard spatial regularizations applied to the unmixing process. The proposed framework is rigorously evaluated using two simulated datasets and a real hyperspectral image. It is compared with competing methods that rely on spatial information derived from a hyperspectral image. The resultsshow that the proposed framework can provide better abundance estimates and, more specifically, can significantly improve the abundance estimates for pixels affected by shadows.

show abstract

A Novel Spectral Unmixing Method Incorporating Spectral Variability Within Endmember Classes

Cited by 36 publications

References 61 publications

Hybrid Spectral Unmixing: Using Artificial Neural Networks for Linear/Non-Linear Switching

Hybrid Spectral Unmixing: Using Artificial Neural Networks for Linear/Non-Linear Switching

Hyperspectral Unmixing With Spectral Variability Using Adaptive Bundles and Double Sparsity

Hyperspectral Image Unmixing With LiDAR Data-Aided Spatial Regularization

Contact Info

Product

Resources

About