Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207488093> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3207488093 endingPage "11041" @default.
- W3207488093 startingPage "11029" @default.
- W3207488093 abstract "Deep transfer-learning based change detection methods are dependent on the availability of sensor-specific pre-trained feature extractors. Such feature extractors are not always available due to lack of training data, especially for hyperspectral sensors and other hyperdimensional images. Moreover models trained on easily available multispectral (RGB/RGB-NIR) images cannot be reused on such hyperdimensional images due to their irregular number of bands. While hyperdimensional images show large number of spectral bands, they generally show much less spatial complexity, thus reducing the requirement of large receptive fields of convolution filters. Recent works in the computer vision have shown that even untrained deep models can yield remarkable result in some tasks like super-resolution and surface reconstruction. This motivates us to make a bold proposition that untrained lightweight deep model, initialized with some weight initialization strategy, can be used to extract useful semantic features from bi-temporal hyperdimensional images. Based on this proposition, we design a novel change detection framework for hyperdimensional images by extracting bi-temporal features using an untrained model and further comparing the extracted features using Deep Change Vector Analysis to distinguish changed pixels from the unchanged ones. We further use the deep change hypervectors to cluster the changed pixels into different semantic groups. We conduct experiments on four change detection datasets: three hyperspectral datasets and a hyperdimensional Polarimetric Synthetic Aperture Radar dataset. The results clearly demonstrate that the proposed method is suitable for change detection in hyperdimensional remote sensing data." @default.
- W3207488093 created "2021-10-25" @default.
- W3207488093 creator A5058025087 @default.
- W3207488093 creator A5070033347 @default.
- W3207488093 creator A5083424027 @default.
- W3207488093 creator A5090588677 @default.
- W3207488093 date "2021-01-01" @default.
- W3207488093 modified "2023-10-14" @default.
- W3207488093 title "Change Detection in Hyperdimensional Images Using Untrained Models" @default.
- W3207488093 cites W1547714734 @default.
- W3207488093 cites W1661193476 @default.
- W3207488093 cites W1677182931 @default.
- W3207488093 cites W1742512077 @default.
- W3207488093 cites W1991927948 @default.
- W3207488093 cites W2054520301 @default.
- W3207488093 cites W2078985447 @default.
- W3207488093 cites W2133003941 @default.
- W3207488093 cites W2133059825 @default.
- W3207488093 cites W2144552105 @default.
- W3207488093 cites W2160544350 @default.
- W3207488093 cites W2332183138 @default.
- W3207488093 cites W2546658262 @default.
- W3207488093 cites W2595144186 @default.
- W3207488093 cites W2752509951 @default.
- W3207488093 cites W2754955826 @default.
- W3207488093 cites W2756481566 @default.
- W3207488093 cites W2757459618 @default.
- W3207488093 cites W2773926432 @default.
- W3207488093 cites W2782517596 @default.
- W3207488093 cites W2782522152 @default.
- W3207488093 cites W2896862629 @default.
- W3207488093 cites W2900587135 @default.
- W3207488093 cites W2901172439 @default.
- W3207488093 cites W2902594250 @default.
- W3207488093 cites W2910587630 @default.
- W3207488093 cites W2962770389 @default.
- W3207488093 cites W2964043336 @default.
- W3207488093 cites W2973014570 @default.
- W3207488093 cites W2979791386 @default.
- W3207488093 cites W2980068277 @default.
- W3207488093 cites W2987767446 @default.
- W3207488093 cites W2997043451 @default.
- W3207488093 cites W2999529768 @default.
- W3207488093 cites W3007098358 @default.
- W3207488093 cites W3017051070 @default.
- W3207488093 cites W3020832687 @default.
- W3207488093 cites W3021083751 @default.
- W3207488093 cites W3035356612 @default.
- W3207488093 cites W3036616251 @default.
- W3207488093 cites W3099831940 @default.
- W3207488093 cites W3103145119 @default.
- W3207488093 cites W3105127913 @default.
- W3207488093 cites W3122887115 @default.
- W3207488093 cites W4240485910 @default.
- W3207488093 doi "https://doi.org/10.1109/jstars.2021.3121556" @default.
- W3207488093 hasPublicationYear "2021" @default.
- W3207488093 type Work @default.
- W3207488093 sameAs 3207488093 @default.
- W3207488093 citedByCount "10" @default.
- W3207488093 countsByYear W32074880932022 @default.
- W3207488093 countsByYear W32074880932023 @default.
- W3207488093 crossrefType "journal-article" @default.
- W3207488093 hasAuthorship W3207488093A5058025087 @default.
- W3207488093 hasAuthorship W3207488093A5070033347 @default.
- W3207488093 hasAuthorship W3207488093A5083424027 @default.
- W3207488093 hasAuthorship W3207488093A5090588677 @default.
- W3207488093 hasBestOaLocation W32074880931 @default.
- W3207488093 hasConcept C154945302 @default.
- W3207488093 hasConcept C203595873 @default.
- W3207488093 hasConcept C31972630 @default.
- W3207488093 hasConcept C41008148 @default.
- W3207488093 hasConceptScore W3207488093C154945302 @default.
- W3207488093 hasConceptScore W3207488093C203595873 @default.
- W3207488093 hasConceptScore W3207488093C31972630 @default.
- W3207488093 hasConceptScore W3207488093C41008148 @default.
- W3207488093 hasFunder F4320321114 @default.
- W3207488093 hasFunder F4320325698 @default.
- W3207488093 hasFunder F4320338335 @default.
- W3207488093 hasLocation W32074880931 @default.
- W3207488093 hasLocation W32074880932 @default.
- W3207488093 hasLocation W32074880933 @default.
- W3207488093 hasOpenAccess W3207488093 @default.
- W3207488093 hasPrimaryLocation W32074880931 @default.
- W3207488093 hasRelatedWork W1914983192 @default.
- W3207488093 hasRelatedWork W1970041046 @default.
- W3207488093 hasRelatedWork W2120507065 @default.
- W3207488093 hasRelatedWork W2131911629 @default.
- W3207488093 hasRelatedWork W2393324510 @default.
- W3207488093 hasRelatedWork W2608348068 @default.
- W3207488093 hasRelatedWork W2613626105 @default.
- W3207488093 hasRelatedWork W2774991885 @default.
- W3207488093 hasRelatedWork W2979649635 @default.
- W3207488093 hasRelatedWork W49138369 @default.
- W3207488093 hasVolume "14" @default.
- W3207488093 isParatext "false" @default.
- W3207488093 isRetracted "false" @default.
- W3207488093 magId "3207488093" @default.
- W3207488093 workType "article" @default.