FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893348249> ?p ?o ?g. }

• W2893348249 endingPage "6257" @default.
• W2893348249 startingPage "6245" @default.
• W2893348249 abstract "Hyperspectral unmixing is an important processing step for many hyperspectral applications, mainly including: 1) estimation of pure spectral signatures (endmembers) and 2) estimation of the abundance of each endmember in each pixel of the image. In recent years, nonnegative matrix factorization (NMF) has been highly attractive for this purpose due to the nonnegativity constraint that is often imposed in the abundance estimation step. However, most of the existing NMF-based methods only consider the information in a single layer while neglecting the hierarchical features with hidden information. To alleviate such limitation, in this paper, we propose a new sparsity-constrained deep NMF with total variation (SDNMF-TV) technique for hyperspectral unmixing. First, by adopting the concept of deep learning, the NMF algorithm is extended to deep NMF model. The proposed model consists of pretraining stage and fine-tuning stage , where the former pretrains all factors layer by layer and the latter is used to reduce the total reconstruction error. Second, in order to exploit adequately the spectral and spatial information included in the original hyperspectral image, we enforce two constraints on the abundance matrix. Specifically, the $L_{1/2}$ constraint is adopted, since the distribution of each endmember is sparse in the 2-D space. The TV regularizer is further introduced to promote piecewise smoothness in abundance maps. For the optimization of the proposed model, multiplicative update rules are derived using the gradient descent method. The effectiveness and superiority of the SDNMF-TV algorithm are demonstrated by comparing with other unmixing methods on both synthetic and real data sets." @default.
• W2893348249 created "2018-10-05" @default.
• W2893348249 creator A5015155189 @default.
• W2893348249 creator A5027835055 @default.
• W2893348249 creator A5033017179 @default.
• W2893348249 creator A5035081074 @default.
• W2893348249 creator A5037162971 @default.
• W2893348249 creator A5054292278 @default.
• W2893348249 date "2018-10-01" @default.
• W2893348249 modified "2023-10-16" @default.
• W2893348249 title "Hyperspectral Unmixing Using Sparsity-Constrained Deep Nonnegative Matrix Factorization With Total Variation" @default.
• W2893348249 cites W1631938343 @default.
• W2893348249 cites W1902016676 @default.
• W2893348249 cites W1915139133 @default.
• W2893348249 cites W1965888395 @default.
• W2893348249 cites W1966798775 @default.
• W2893348249 cites W1967381020 @default.
• W2893348249 cites W1969238202 @default.
• W2893348249 cites W1974448798 @default.
• W2893348249 cites W2009576740 @default.
• W2893348249 cites W2019149505 @default.
• W2893348249 cites W2027357158 @default.
• W2893348249 cites W2029316659 @default.
• W2893348249 cites W2029786966 @default.
• W2893348249 cites W2032944446 @default.
• W2893348249 cites W2041891835 @default.
• W2893348249 cites W2042294722 @default.
• W2893348249 cites W2054854521 @default.
• W2893348249 cites W2063069198 @default.
• W2893348249 cites W2070424424 @default.
• W2893348249 cites W2072599882 @default.
• W2893348249 cites W2084252873 @default.
• W2893348249 cites W2103559027 @default.
• W2893348249 cites W2108433027 @default.
• W2893348249 cites W2122976738 @default.
• W2893348249 cites W2125298866 @default.
• W2893348249 cites W2127062304 @default.
• W2893348249 cites W2127934268 @default.
• W2893348249 cites W2136922672 @default.
• W2893348249 cites W2141494774 @default.
• W2893348249 cites W2142224912 @default.
• W2893348249 cites W2156787910 @default.
• W2893348249 cites W2157321686 @default.
• W2893348249 cites W2162888866 @default.
• W2893348249 cites W2163886442 @default.
• W2893348249 cites W2165755981 @default.
• W2893348249 cites W2313932751 @default.
• W2893348249 cites W2318512420 @default.
• W2893348249 cites W2342750892 @default.
• W2893348249 cites W2344025572 @default.
• W2893348249 cites W2402292288 @default.
• W2893348249 cites W2490201121 @default.
• W2893348249 cites W2551961488 @default.
• W2893348249 cites W2587548727 @default.
• W2893348249 cites W2592312604 @default.
• W2893348249 cites W2604977491 @default.
• W2893348249 cites W2605327034 @default.
• W2893348249 cites W2617737158 @default.
• W2893348249 cites W2753754894 @default.
• W2893348249 cites W2765455392 @default.
• W2893348249 cites W2771346875 @default.
• W2893348249 cites W2774528199 @default.
• W2893348249 cites W3102274762 @default.
• W2893348249 cites W3122463936 @default.
• W2893348249 doi "https://doi.org/10.1109/tgrs.2018.2834567" @default.
• W2893348249 hasPublicationYear "2018" @default.
• W2893348249 type Work @default.
• W2893348249 sameAs 2893348249 @default.
• W2893348249 citedByCount "94" @default.
• W2893348249 countsByYear W28933482492018 @default.
• W2893348249 countsByYear W28933482492019 @default.
• W2893348249 countsByYear W28933482492020 @default.
• W2893348249 countsByYear W28933482492021 @default.
• W2893348249 countsByYear W28933482492022 @default.
• W2893348249 countsByYear W28933482492023 @default.
• W2893348249 crossrefType "journal-article" @default.
• W2893348249 hasAuthorship W2893348249A5015155189 @default.
• W2893348249 hasAuthorship W2893348249A5027835055 @default.
• W2893348249 hasAuthorship W2893348249A5033017179 @default.
• W2893348249 hasAuthorship W2893348249A5035081074 @default.
• W2893348249 hasAuthorship W2893348249A5037162971 @default.
• W2893348249 hasAuthorship W2893348249A5054292278 @default.
• W2893348249 hasConcept C121332964 @default.
• W2893348249 hasConcept C152671427 @default.
• W2893348249 hasConcept C153180895 @default.
• W2893348249 hasConcept C154945302 @default.
• W2893348249 hasConcept C158693339 @default.
• W2893348249 hasConcept C159078339 @default.
• W2893348249 hasConcept C2778334786 @default.
• W2893348249 hasConcept C31972630 @default.
• W2893348249 hasConcept C41008148 @default.
• W2893348249 hasConcept C42355184 @default.
• W2893348249 hasConcept C44870925 @default.
• W2893348249 hasConcept C62520636 @default.
• W2893348249 hasConceptScore W2893348249C121332964 @default.
• W2893348249 hasConceptScore W2893348249C152671427 @default.
• W2893348249 hasConceptScore W2893348249C153180895 @default.
• W2893348249 hasConceptScore W2893348249C154945302 @default.

• next