Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203407718> ?p ?o ?g. }
- W3203407718 endingPage "10732" @default.
- W3203407718 startingPage "10716" @default.
- W3203407718 abstract "To accurately extract various ground objects from PolSAR images is a challenging research topic. The deep convolutional neural networks are widely used in SAR segmentation due to their remarkable performance in optical remote sensing images. However, they are still limited by the geometric deformation of the objects, the strong scattering interference among adjacent objects and the difficulty in distinguishing similar things. A large part of the reason lies in the insufficient utilization and the damage of feature mining for PolSAR data. In this paper, focusing on the scattering matrix and the polarimetric coherency matrix, a polarimetric space reconstruction network is proposed. First, to maintain the relatively initial spatial constraints and the complete polarimetric information, the inputs are arranged by a spatial amplification coding method for the polarimetric coherency matrix and scattering matrix. Second, a statistics enhancement module based on scattering characteristics is proposed to mine the differential expression among multiple scattering and polarimetric components, which supplements the local feature representation of convolutional operators. Third, the designed dual self-attention mechanism can capture the amplitude and phase relations of matrix element context adaptively. The proposed method keeps the spatiality of each scattering vector and fully unearths the complementary information involved in the full polarimetric data. Moreover, it accomplishes the accurate land cover classification for PolSAR images, especially the traditional confusing categories, such as water and roads. The experimental results on the E-SAR, AIRSAR, Gaofen-3 and RADARSAT-2 datasets show that the proposed method is effective and promising for PolSAR image segmentation." @default.
- W3203407718 created "2021-10-11" @default.
- W3203407718 creator A5002059265 @default.
- W3203407718 creator A5005905514 @default.
- W3203407718 creator A5023538862 @default.
- W3203407718 creator A5051658832 @default.
- W3203407718 creator A5072018831 @default.
- W3203407718 date "2021-01-01" @default.
- W3203407718 modified "2023-10-17" @default.
- W3203407718 title "PSRN: Polarimetric Space Reconstruction Network for PolSAR Image Semantic Segmentation" @default.
- W3203407718 cites W1903029394 @default.
- W3203407718 cites W1992350595 @default.
- W3203407718 cites W2049865414 @default.
- W3203407718 cites W2057621897 @default.
- W3203407718 cites W2078985447 @default.
- W3203407718 cites W2097272115 @default.
- W3203407718 cites W2102605133 @default.
- W3203407718 cites W2130762895 @default.
- W3203407718 cites W2133989913 @default.
- W3203407718 cites W2194775991 @default.
- W3203407718 cites W2314847086 @default.
- W3203407718 cites W2345055757 @default.
- W3203407718 cites W2370317051 @default.
- W3203407718 cites W2410153343 @default.
- W3203407718 cites W2412782625 @default.
- W3203407718 cites W2560023338 @default.
- W3203407718 cites W2570343428 @default.
- W3203407718 cites W2586898334 @default.
- W3203407718 cites W2623886156 @default.
- W3203407718 cites W2754361766 @default.
- W3203407718 cites W2759117176 @default.
- W3203407718 cites W2782522152 @default.
- W3203407718 cites W2793189836 @default.
- W3203407718 cites W2799213142 @default.
- W3203407718 cites W2885683051 @default.
- W3203407718 cites W2892123021 @default.
- W3203407718 cites W2895222021 @default.
- W3203407718 cites W2962914239 @default.
- W3203407718 cites W2963037989 @default.
- W3203407718 cites W2963125010 @default.
- W3203407718 cites W2963727650 @default.
- W3203407718 cites W2963881378 @default.
- W3203407718 cites W2979706722 @default.
- W3203407718 cites W2995801068 @default.
- W3203407718 cites W3004187475 @default.
- W3203407718 cites W3015546692 @default.
- W3203407718 cites W3032837604 @default.
- W3203407718 cites W3049670509 @default.
- W3203407718 cites W3080181119 @default.
- W3203407718 cites W3083065220 @default.
- W3203407718 cites W3091945887 @default.
- W3203407718 cites W3105636206 @default.
- W3203407718 cites W3111896518 @default.
- W3203407718 cites W3124566001 @default.
- W3203407718 cites W3131937156 @default.
- W3203407718 cites W3157192212 @default.
- W3203407718 cites W3158311779 @default.
- W3203407718 cites W3160032272 @default.
- W3203407718 cites W3176626319 @default.
- W3203407718 doi "https://doi.org/10.1109/jstars.2021.3116062" @default.
- W3203407718 hasPublicationYear "2021" @default.
- W3203407718 type Work @default.
- W3203407718 sameAs 3203407718 @default.
- W3203407718 citedByCount "8" @default.
- W3203407718 countsByYear W32034077182022 @default.
- W3203407718 countsByYear W32034077182023 @default.
- W3203407718 crossrefType "journal-article" @default.
- W3203407718 hasAuthorship W3203407718A5002059265 @default.
- W3203407718 hasAuthorship W3203407718A5005905514 @default.
- W3203407718 hasAuthorship W3203407718A5023538862 @default.
- W3203407718 hasAuthorship W3203407718A5051658832 @default.
- W3203407718 hasAuthorship W3203407718A5072018831 @default.
- W3203407718 hasBestOaLocation W32034077181 @default.
- W3203407718 hasConcept C120665830 @default.
- W3203407718 hasConcept C121332964 @default.
- W3203407718 hasConcept C138885662 @default.
- W3203407718 hasConcept C153180895 @default.
- W3203407718 hasConcept C154945302 @default.
- W3203407718 hasConcept C191486275 @default.
- W3203407718 hasConcept C205649164 @default.
- W3203407718 hasConcept C2776401178 @default.
- W3203407718 hasConcept C28493345 @default.
- W3203407718 hasConcept C31972630 @default.
- W3203407718 hasConcept C41008148 @default.
- W3203407718 hasConcept C41895202 @default.
- W3203407718 hasConcept C62649853 @default.
- W3203407718 hasConcept C81363708 @default.
- W3203407718 hasConcept C83665646 @default.
- W3203407718 hasConcept C89600930 @default.
- W3203407718 hasConceptScore W3203407718C120665830 @default.
- W3203407718 hasConceptScore W3203407718C121332964 @default.
- W3203407718 hasConceptScore W3203407718C138885662 @default.
- W3203407718 hasConceptScore W3203407718C153180895 @default.
- W3203407718 hasConceptScore W3203407718C154945302 @default.
- W3203407718 hasConceptScore W3203407718C191486275 @default.
- W3203407718 hasConceptScore W3203407718C205649164 @default.
- W3203407718 hasConceptScore W3203407718C2776401178 @default.
- W3203407718 hasConceptScore W3203407718C28493345 @default.