Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890585763> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2890585763 abstract "Hyperspectral image unmixing is a source separation problem aiming at recovering the spectra of the pure materials of the observed scene (called endmembers), as well as their relative proportions in each pixel of the image (called abundances). The variability of the materials has recently received a lot of attention in the community. In particular, a consequent number of models and algorithms have been proposed to estimate pixel-wise endmembers to account for their variability. These algorithms often rely on classical endmem-ber extraction algorithms to provide reference spectra. In difficult scenarios with shadows and significant variability these algorithms may fail. In this paper, we address this issue in the Extended Linear Mixing Model framework by considering that an endmember is a direction in the feature space, rather than a single point. Under this paradigm, we show that using k- means clustering with the cosine similarity outperforms geometric endmember extraction algorithms. We also design an algorithm to refine the estimation of the endmember directions, and to account for both illumination and intrinsic variability effects. We show the potential of the proposed algorithm on a synthetic dataset using real world spectra with variability, and a challenging real dataset of a natural scene." @default.
- W2890585763 created "2018-09-27" @default.
- W2890585763 creator A5005014399 @default.
- W2890585763 creator A5035508615 @default.
- W2890585763 creator A5046811680 @default.
- W2890585763 date "2018-04-01" @default.
- W2890585763 modified "2023-10-17" @default.
- W2890585763 title "Endmembers as Directional Data for Robust Material Variability Retrieval in Hyperspectral Image Unmixing" @default.
- W2890585763 cites W1524571335 @default.
- W2890585763 cites W1963659868 @default.
- W2890585763 cites W1972293418 @default.
- W2890585763 cites W2008233110 @default.
- W2890585763 cites W2037328426 @default.
- W2890585763 cites W2060147006 @default.
- W2890585763 cites W2087263574 @default.
- W2890585763 cites W2107219953 @default.
- W2890585763 cites W2122976738 @default.
- W2890585763 cites W2127062304 @default.
- W2890585763 cites W2157321686 @default.
- W2890585763 cites W2163886442 @default.
- W2890585763 cites W2415341181 @default.
- W2890585763 cites W2680647589 @default.
- W2890585763 cites W3098446347 @default.
- W2890585763 cites W3122463936 @default.
- W2890585763 cites W4233760599 @default.
- W2890585763 cites W972216811 @default.
- W2890585763 doi "https://doi.org/10.1109/icassp.2018.8462256" @default.
- W2890585763 hasPublicationYear "2018" @default.
- W2890585763 type Work @default.
- W2890585763 sameAs 2890585763 @default.
- W2890585763 citedByCount "5" @default.
- W2890585763 countsByYear W28905857632018 @default.
- W2890585763 countsByYear W28905857632019 @default.
- W2890585763 countsByYear W28905857632020 @default.
- W2890585763 countsByYear W28905857632021 @default.
- W2890585763 crossrefType "proceedings-article" @default.
- W2890585763 hasAuthorship W2890585763A5005014399 @default.
- W2890585763 hasAuthorship W2890585763A5035508615 @default.
- W2890585763 hasAuthorship W2890585763A5046811680 @default.
- W2890585763 hasBestOaLocation W28905857632 @default.
- W2890585763 hasConcept C103278499 @default.
- W2890585763 hasConcept C11413529 @default.
- W2890585763 hasConcept C115961682 @default.
- W2890585763 hasConcept C138885662 @default.
- W2890585763 hasConcept C153180895 @default.
- W2890585763 hasConcept C154945302 @default.
- W2890585763 hasConcept C159078339 @default.
- W2890585763 hasConcept C160633673 @default.
- W2890585763 hasConcept C2776401178 @default.
- W2890585763 hasConcept C41008148 @default.
- W2890585763 hasConcept C41895202 @default.
- W2890585763 hasConcept C52622490 @default.
- W2890585763 hasConcept C58237817 @default.
- W2890585763 hasConcept C73555534 @default.
- W2890585763 hasConceptScore W2890585763C103278499 @default.
- W2890585763 hasConceptScore W2890585763C11413529 @default.
- W2890585763 hasConceptScore W2890585763C115961682 @default.
- W2890585763 hasConceptScore W2890585763C138885662 @default.
- W2890585763 hasConceptScore W2890585763C153180895 @default.
- W2890585763 hasConceptScore W2890585763C154945302 @default.
- W2890585763 hasConceptScore W2890585763C159078339 @default.
- W2890585763 hasConceptScore W2890585763C160633673 @default.
- W2890585763 hasConceptScore W2890585763C2776401178 @default.
- W2890585763 hasConceptScore W2890585763C41008148 @default.
- W2890585763 hasConceptScore W2890585763C41895202 @default.
- W2890585763 hasConceptScore W2890585763C52622490 @default.
- W2890585763 hasConceptScore W2890585763C58237817 @default.
- W2890585763 hasConceptScore W2890585763C73555534 @default.
- W2890585763 hasLocation W28905857631 @default.
- W2890585763 hasLocation W28905857632 @default.
- W2890585763 hasLocation W28905857633 @default.
- W2890585763 hasLocation W28905857634 @default.
- W2890585763 hasLocation W28905857635 @default.
- W2890585763 hasOpenAccess W2890585763 @default.
- W2890585763 hasPrimaryLocation W28905857631 @default.
- W2890585763 hasRelatedWork W1990914742 @default.
- W2890585763 hasRelatedWork W2006559622 @default.
- W2890585763 hasRelatedWork W2037328426 @default.
- W2890585763 hasRelatedWork W2040756827 @default.
- W2890585763 hasRelatedWork W2051769241 @default.
- W2890585763 hasRelatedWork W2138418872 @default.
- W2890585763 hasRelatedWork W2890371384 @default.
- W2890585763 hasRelatedWork W2891033441 @default.
- W2890585763 hasRelatedWork W3106536224 @default.
- W2890585763 hasRelatedWork W4379116984 @default.
- W2890585763 isParatext "false" @default.
- W2890585763 isRetracted "false" @default.
- W2890585763 magId "2890585763" @default.
- W2890585763 workType "article" @default.