FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3157192212> ?p ?o ?g. }

• W3157192212 endingPage "6623" @default.
• W3157192212 startingPage "6608" @default.
• W3157192212 abstract "The building extraction from synthetic aperture radar (SAR) images has always been a challenging research topic. Recently, the deep convolution neural network brings excellent improvements in SAR segmentation. The fully convolutional network and other variants are widely transferred to the SAR studies because of their high precision in optical images. They are still limited by their processing in terms of the geometric distortion of buildings, the variability of building structures, and scattering interference between adjacent targets in the SAR images. In this article, a unified framework called selective spatial pyramid dilated (SSPD) network is proposed for the fine building segmentation in SAR images. First, we propose a novel encoder–decoder structure for the fine building feature reconstruction. The enhanced encoder and the dual-stage decoder, composed of the CBM and the SSPD module, extract and recover the crucial multiscale information better. Second, we design the multilayer SSPD module based on the selective spatial attention. The multiscale building information with different attention on multiple branches is combined, optimized, and adaptively selected for adaptive filtering and extracting features of complex multiscale building targets in SAR images. Third, according to the building features and SAR imaging mechanism, a new loss function called L-shape weighting loss (LWloss) is proposed to heighten the attention on the L-shape footprint characteristics of the buildings and reduce the missing detection of line buildings. Besides, LWloss can also alleviate the class imbalance problem in the optimization stage. Finally, the experiments on a large-scene SAR image dataset demonstrate the effectiveness of the proposed method and verify its superiority over other approaches, such as the region-based Markov random field, U-net, and DeepLabv3+." @default.
• W3157192212 created "2021-05-10" @default.
• W3157192212 creator A5002059265 @default.
• W3157192212 creator A5002110023 @default.
• W3157192212 creator A5005905514 @default.
• W3157192212 creator A5023538862 @default.
• W3157192212 creator A5051658832 @default.
• W3157192212 creator A5053611461 @default.
• W3157192212 date "2021-01-01" @default.
• W3157192212 modified "2023-10-17" @default.
• W3157192212 title "Fine Building Segmentation in High-Resolution SAR Images Via Selective Pyramid Dilated Network" @default.
• W3157192212 cites W1978818813 @default.
• W3157192212 cites W1989222601 @default.
• W3157192212 cites W1989961619 @default.
• W3157192212 cites W1994963693 @default.
• W3157192212 cites W1996236898 @default.
• W3157192212 cites W2030233108 @default.
• W3157192212 cites W2035596087 @default.
• W3157192212 cites W2052606545 @default.
• W3157192212 cites W2064856988 @default.
• W3157192212 cites W2073774685 @default.
• W3157192212 cites W2112106107 @default.
• W3157192212 cites W2117438495 @default.
• W3157192212 cites W2133059825 @default.
• W3157192212 cites W2138237320 @default.
• W3157192212 cites W2144615653 @default.
• W3157192212 cites W2163431839 @default.
• W3157192212 cites W2163884840 @default.
• W3157192212 cites W2194775991 @default.
• W3157192212 cites W2288122362 @default.
• W3157192212 cites W2319358180 @default.
• W3157192212 cites W2484840579 @default.
• W3157192212 cites W2531409750 @default.
• W3157192212 cites W2560023338 @default.
• W3157192212 cites W2574739416 @default.
• W3157192212 cites W2752782242 @default.
• W3157192212 cites W2754361766 @default.
• W3157192212 cites W2762294195 @default.
• W3157192212 cites W2779850592 @default.
• W3157192212 cites W2786492053 @default.
• W3157192212 cites W2846519445 @default.
• W3157192212 cites W2892123021 @default.
• W3157192212 cites W2893747990 @default.
• W3157192212 cites W2897151373 @default.
• W3157192212 cites W2897902589 @default.
• W3157192212 cites W2917458084 @default.
• W3157192212 cites W2922509574 @default.
• W3157192212 cites W2945957599 @default.
• W3157192212 cites W2957158099 @default.
• W3157192212 cites W2961699889 @default.
• W3157192212 cites W2962914239 @default.
• W3157192212 cites W2963125010 @default.
• W3157192212 cites W2963881378 @default.
• W3157192212 cites W2965270000 @default.
• W3157192212 cites W2968090415 @default.
• W3157192212 cites W2979314512 @default.
• W3157192212 cites W2982848826 @default.
• W3157192212 cites W2986028557 @default.
• W3157192212 cites W2987396770 @default.
• W3157192212 cites W2995801068 @default.
• W3157192212 cites W3004492228 @default.
• W3157192212 cites W3005857981 @default.
• W3157192212 cites W3012991496 @default.
• W3157192212 cites W3032837604 @default.
• W3157192212 cites W3035248706 @default.
• W3157192212 cites W3098740429 @default.
• W3157192212 cites W3105636206 @default.
• W3157192212 cites W3106141888 @default.
• W3157192212 cites W3117535430 @default.
• W3157192212 doi "https://doi.org/10.1109/jstars.2021.3076085" @default.
• W3157192212 hasPublicationYear "2021" @default.
• W3157192212 type Work @default.
• W3157192212 sameAs 3157192212 @default.
• W3157192212 citedByCount "22" @default.
• W3157192212 countsByYear W31571922122021 @default.
• W3157192212 countsByYear W31571922122022 @default.
• W3157192212 countsByYear W31571922122023 @default.
• W3157192212 crossrefType "journal-article" @default.
• W3157192212 hasAuthorship W3157192212A5002059265 @default.
• W3157192212 hasAuthorship W3157192212A5002110023 @default.
• W3157192212 hasAuthorship W3157192212A5005905514 @default.
• W3157192212 hasAuthorship W3157192212A5023538862 @default.
• W3157192212 hasAuthorship W3157192212A5051658832 @default.
• W3157192212 hasAuthorship W3157192212A5053611461 @default.
• W3157192212 hasBestOaLocation W31571922121 @default.
• W3157192212 hasConcept C108583219 @default.
• W3157192212 hasConcept C120665830 @default.
• W3157192212 hasConcept C121332964 @default.
• W3157192212 hasConcept C124504099 @default.
• W3157192212 hasConcept C138885662 @default.
• W3157192212 hasConcept C142575187 @default.
• W3157192212 hasConcept C153180895 @default.
• W3157192212 hasConcept C154945302 @default.
• W3157192212 hasConcept C2776401178 @default.
• W3157192212 hasConcept C31972630 @default.
• W3157192212 hasConcept C41008148 @default.
• W3157192212 hasConcept C41895202 @default.
• W3157192212 hasConcept C52622490 @default.

• next