Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery

By Daniel C. Heinz, Chein-I. Chang. IEEE Transactions on Geoscience and Remote Sensing, 2001

1,869 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/47d15dfd9d4e06fdb596803bf1c5e9a7661183a3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

1. Nicolas Gillis
2. Antonio J. Plaza
3. José M. Bioucas-Dias
4. Jocelyn Chanussot
5. Sen Jia
6. Y. Qian
7. Naoto Yokoya
8. Jean-Yves Tourneret

In Ecology

1. Jocelyn Chanussot
2. Qian Du
3. Antonio J. Plaza
4. Danfeng Hong
5. Paul D. Gader
6. Sen Jia
7. Antonio Robles-Kelly
8. Jun Zhou

In Media Technology

1. José M. Bioucas-Dias
2. Jocelyn Chanussot
3. Antonio J. Plaza
4. Shutao Li
5. Nicolas Gillis
6. Leyuan Fang
7. Naoto Yokoya
8. Y. Qian

Citations in the corpus

• Hyperspectral Pansharpening: A Review (2015, methodology): “The abundance sum-to-one constraint is implemented using a method given in [77], where the data and signature matrices are augmented by a row of constants.”
• Similarity-Based Unsupervised Band Selection for Hyperspectral Image Analysis (2008, methodology): “The concept in the LP-based band selection was originally used in the UFCLSLU for endmember pixel selection in [10], which means that a pixel with the maximum reconstruction error, using the linear combination of existing endmember pixels, is the most distinctive pixel.”
• A Review of Nonlinear Hyperspectral Unmixing Methods (2014, methodology): “This kernel was then used in the kernelized fully-constrained least-squares unmixing (FCLSU) algorithm [19], [76] to unmix the data.”
• An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing (2018, background): “with the two reasonable constraints adapting to reality [26] as follows: 1) the abundance non-negative constraint (ANC), namely xk 0; and 2) the abundance sum-to-one constraint (ASC), namely 1Pxk = 1 (1P = [1, 1, .”
• A Signal Processing Perspective on Hyperspectral Unmixing: Insights from Remote Sensing (2014, background): “Alternatively, one can design dedicated algorithms for (4) to have more efficient implementations; this is a more popular option in the field [13]–[15].”
• Joint Bayesian Endmember Extraction and Linear Unmixing for Hyperspectral Imagery (2009, methodology): “The inversion step can use various strategies such as least square estimation [17], maximum likelihood estimation [18] and Bayesian estimation [19].”
• Collaborative Sparse Regression for Hyperspectral Unmixing (2014, background): “Linear spectral unmixing [2], [4]–[7] is a standard technique for spectral mixture analysis that infers a set of pure spectral signatures, called endmembers, and the fractions of these endmembers, called abundances, in each pixel of the scene.”
• Coupled Nonnegative Matrix Factorization Unmixing for Hyperspectral and Multispectral Data Fusion (2012, neutral): “method given in [35].”
• Manifold Regularized Sparse NMF for Hyperspectral Unmixing (2013, methodology): “, 1PS = 1 T N , a simple but effective technique in [14] is employed here.”
• GETNET: A General End-to-End 2-D CNN Framework for Hyperspectral Image Change Detection (2019, methodology): “To estimate the parameters, the fully constrained least squares (FCLS) [31] method is adopted.”