Matches in SemOpenAlex for { <https://semopenalex.org/work/W2956367483> ?p ?o ?g. }
- W2956367483 endingPage "501" @default.
- W2956367483 startingPage "487" @default.
- W2956367483 abstract "This paper develops a novel hyperspectral image (HSI) classification framework by exploiting the spectral-spatial features of multiscale superpixels via recurrent neural networks with stacked autoencoders. The superpixels can be used to segment an HSI into shape-adaptive regions, and multiscale superpixels can capture the object information more accurately. Therefore, the superpixel-based classification methods have been studied by many researchers. In this paper, we propose a multiscale superpixel-based classification method. In contrast to current research, the proposed method not only captures the features of each scale but also considers the correlation among different scales via recurrent neural networks. In this way, the spectral-spatial information within a superpixel is more efficiently exploited. In this paper, we first segment the HSI from coarse to fine scales using the superpixels. Then, the spatial features within each superpixel and among superpixels are sufficiently exploited by the local and nonlocal similarity measure. Finally, recurrent neural networks with stacked autoencoders are proposed to learn the high-level multiscale spectral-spatial features. Experiments are conducted on real HSI datasets. The results demonstrate the superiority of the proposed method over several well-known methods in both visual appearance and classification accuracy." @default.
- W2956367483 created "2019-07-23" @default.
- W2956367483 creator A5005772506 @default.
- W2956367483 creator A5017377911 @default.
- W2956367483 date "2020-02-01" @default.
- W2956367483 modified "2023-10-16" @default.
- W2956367483 title "Multiscale Superpixel-Based Hyperspectral Image Classification Using Recurrent Neural Networks With Stacked Autoencoders" @default.
- W2956367483 cites W1843514792 @default.
- W2956367483 cites W1922904362 @default.
- W2956367483 cites W1939429412 @default.
- W2956367483 cites W1950365613 @default.
- W2956367483 cites W1966580635 @default.
- W2956367483 cites W1970945970 @default.
- W2956367483 cites W1971891445 @default.
- W2956367483 cites W1974211415 @default.
- W2956367483 cites W1985468858 @default.
- W2956367483 cites W1998030734 @default.
- W2956367483 cites W2029316659 @default.
- W2956367483 cites W2046373373 @default.
- W2956367483 cites W2049444988 @default.
- W2956367483 cites W2085529604 @default.
- W2956367483 cites W2090424610 @default.
- W2956367483 cites W2103094532 @default.
- W2956367483 cites W2110798204 @default.
- W2956367483 cites W2112796928 @default.
- W2956367483 cites W2114819256 @default.
- W2956367483 cites W2131864940 @default.
- W2956367483 cites W2136922672 @default.
- W2956367483 cites W2144151128 @default.
- W2956367483 cites W2149471024 @default.
- W2956367483 cites W2151599207 @default.
- W2956367483 cites W2164330327 @default.
- W2956367483 cites W2253590344 @default.
- W2956367483 cites W2261067923 @default.
- W2956367483 cites W2267317359 @default.
- W2956367483 cites W2310141728 @default.
- W2956367483 cites W2314785379 @default.
- W2956367483 cites W2344173806 @default.
- W2956367483 cites W2345128667 @default.
- W2956367483 cites W2417947228 @default.
- W2956367483 cites W2500751094 @default.
- W2956367483 cites W2509348655 @default.
- W2956367483 cites W2518831014 @default.
- W2956367483 cites W2523396434 @default.
- W2956367483 cites W2533102868 @default.
- W2956367483 cites W2547080737 @default.
- W2956367483 cites W2548791488 @default.
- W2956367483 cites W2560809721 @default.
- W2956367483 cites W2598551616 @default.
- W2956367483 cites W2737996023 @default.
- W2956367483 cites W2750722971 @default.
- W2956367483 cites W2790473231 @default.
- W2956367483 cites W4240485910 @default.
- W2956367483 doi "https://doi.org/10.1109/tmm.2019.2928491" @default.
- W2956367483 hasPublicationYear "2020" @default.
- W2956367483 type Work @default.
- W2956367483 sameAs 2956367483 @default.
- W2956367483 citedByCount "46" @default.
- W2956367483 countsByYear W29563674832020 @default.
- W2956367483 countsByYear W29563674832021 @default.
- W2956367483 countsByYear W29563674832022 @default.
- W2956367483 countsByYear W29563674832023 @default.
- W2956367483 crossrefType "journal-article" @default.
- W2956367483 hasAuthorship W2956367483A5005772506 @default.
- W2956367483 hasAuthorship W2956367483A5017377911 @default.
- W2956367483 hasConcept C115961682 @default.
- W2956367483 hasConcept C153180895 @default.
- W2956367483 hasConcept C154945302 @default.
- W2956367483 hasConcept C159078339 @default.
- W2956367483 hasConcept C31972630 @default.
- W2956367483 hasConcept C41008148 @default.
- W2956367483 hasConcept C50644808 @default.
- W2956367483 hasConcept C75294576 @default.
- W2956367483 hasConceptScore W2956367483C115961682 @default.
- W2956367483 hasConceptScore W2956367483C153180895 @default.
- W2956367483 hasConceptScore W2956367483C154945302 @default.
- W2956367483 hasConceptScore W2956367483C159078339 @default.
- W2956367483 hasConceptScore W2956367483C31972630 @default.
- W2956367483 hasConceptScore W2956367483C41008148 @default.
- W2956367483 hasConceptScore W2956367483C50644808 @default.
- W2956367483 hasConceptScore W2956367483C75294576 @default.
- W2956367483 hasIssue "2" @default.
- W2956367483 hasLocation W29563674831 @default.
- W2956367483 hasOpenAccess W2956367483 @default.
- W2956367483 hasPrimaryLocation W29563674831 @default.
- W2956367483 hasRelatedWork W2020128215 @default.
- W2956367483 hasRelatedWork W2028628118 @default.
- W2956367483 hasRelatedWork W2130228941 @default.
- W2956367483 hasRelatedWork W2161229648 @default.
- W2956367483 hasRelatedWork W2509146328 @default.
- W2956367483 hasRelatedWork W2540922529 @default.
- W2956367483 hasRelatedWork W2742991909 @default.
- W2956367483 hasRelatedWork W2807839383 @default.
- W2956367483 hasRelatedWork W2993674027 @default.
- W2956367483 hasRelatedWork W3173596272 @default.
- W2956367483 hasVolume "22" @default.
- W2956367483 isParatext "false" @default.
- W2956367483 isRetracted "false" @default.