Jul 22, 2020 · Hyperspectral unmixing is a crucial task for hyperspectral images (HSI) processing, which estimates the proportions of constituent materials ...
By hypergraph learning, the spatial–spectral joint structure as a regularization term is incorporated into the sparse unmixing model to enforce the.
... spectral un Mixing methods. Expand. Add to Library. Alert. 1 Excerpt. Spatial Graph Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing.
May 23, 2023 · In our model, dual-graph regularization is introduced to learn the local structure of the data and feature space simultaneously, so that the ...
Nov 3, 2014 · Spectral unmixing problem refers to decomposing these pixels into a set of endmembers and abundance fractions. Due to nonnegativity constraint ...
Nov 11, 2022 · Summary Hyperspectral unmixing is a crucial technique for exploiting remotely sensed hyperspectral data, which aims to estimate a set of ...
Then the global similar graph for materials is used as a robust spatial prior to improve the quality of the hyperspectral unmixing. 2) We design an objective ...
Spatial Group Sparsity Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing. IEEE Trans. Geosci. Remote Sens. 2017, 55, 6287–6304 ...
Total Variation Regularized Reweighted Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing ... Adaptive Graph Regularized Deep Semi-nonnegative ...
Sep 24, 2020 · Some graph regularization techniques for hyperspectral imaging include graph NMF (GNMF) [29], structured sparse regularized NMF (SS-NMF) [30], ...