FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287958190> ?p ?o ?g. }

• W4287958190 endingPage "102930" @default.
• W4287958190 startingPage "102930" @default.
• W4287958190 abstract "Up-to-date building maps are fundamental to urban development and analysis. However, detecting buildings from images with different spatial resolutions and ground object patterns from various imaging sensors is a challenge. Current models mostly have difficulties in extracting buildings with poor boundaries due to the various building appearances and sizes. Moreover, most published methods are trained and evaluated on subsets from the same dataset whose images are captured from one imaging sensor with similar ground object patterns, making it difficult to evaluate the transferability objectively. To address this issue, a spiking neural network in the frequency domain (SNNFD) is proposed to enhance the model transferability and the feature capability of buildings with different sizes by synthesizing frequency domain and spatial domain learning. Spiking convolution is adopted in the frequency learning module to enhance the model learning ability by mimicking the learning process of human brain. The learned frequency features are concatenated and transformed to the spatial domain, and used to generate building-extraction result images by convolution networks. SNNFD is evaluated on two datasets with different spatial resolutions (0.3–2.5 m) from different imaging sensors (Quickbird, Worldview, IKONOS, ZY-3) of different study areas (worldwide). It is compared with five recently proposed semantic segmentation frameworks (Unet, Segnet, DeepLabv3, BiSeNet, F3-Net), and obtains a minimum of 6.33 % higher accuracy with a strong transferability in detecting different sizes of building instances. Specifically, the proposed model improves the segmentation performance of small building instances by at least 6.5 % compared with the five segmentation frameworks through synthesis of spiking convolution in the frequency learning domain in the model construction. Moreover, details of building boundaries are better maintained by SNNFD, offering the possibility of detecting buildings for practical applications." @default.
• W4287958190 created "2022-07-26" @default.
• W4287958190 creator A5043839950 @default.
• W4287958190 creator A5051364953 @default.
• W4287958190 creator A5052137824 @default.
• W4287958190 creator A5072519607 @default.
• W4287958190 creator A5073216396 @default.
• W4287958190 date "2022-08-01" @default.
• W4287958190 modified "2023-10-14" @default.
• W4287958190 title "SNNFD, spiking neural segmentation network in frequency domain using high spatial resolution images for building extraction" @default.
• W4287958190 cites W1570411240 @default.
• W4287958190 cites W1903029394 @default.
• W4287958190 cites W2020676607 @default.
• W4287958190 cites W2031614119 @default.
• W4287958190 cites W2039573396 @default.
• W4287958190 cites W2412782625 @default.
• W4287958190 cites W2609402060 @default.
• W4287958190 cites W2782522152 @default.
• W4287958190 cites W2789255992 @default.
• W4287958190 cites W2884367402 @default.
• W4287958190 cites W2888889084 @default.
• W4287958190 cites W2908320224 @default.
• W4287958190 cites W2915731581 @default.
• W4287958190 cites W2922102451 @default.
• W4287958190 cites W2939647427 @default.
• W4287958190 cites W2948696683 @default.
• W4287958190 cites W2963525222 @default.
• W4287958190 cites W2963881378 @default.
• W4287958190 cites W2979879900 @default.
• W4287958190 cites W2991441757 @default.
• W4287958190 cites W3007489506 @default.
• W4287958190 cites W3046533531 @default.
• W4287958190 cites W3093130013 @default.
• W4287958190 cites W3094728142 @default.
• W4287958190 cites W3106250896 @default.
• W4287958190 cites W3137744231 @default.
• W4287958190 cites W3154459869 @default.
• W4287958190 cites W3156066202 @default.
• W4287958190 cites W3217529357 @default.
• W4287958190 doi "https://doi.org/10.1016/j.jag.2022.102930" @default.
• W4287958190 hasPublicationYear "2022" @default.
• W4287958190 type Work @default.
• W4287958190 citedByCount "6" @default.
• W4287958190 countsByYear W42879581902022 @default.
• W4287958190 countsByYear W42879581902023 @default.
• W4287958190 crossrefType "journal-article" @default.
• W4287958190 hasAuthorship W4287958190A5043839950 @default.
• W4287958190 hasAuthorship W4287958190A5051364953 @default.
• W4287958190 hasAuthorship W4287958190A5052137824 @default.
• W4287958190 hasAuthorship W4287958190A5072519607 @default.
• W4287958190 hasAuthorship W4287958190A5073216396 @default.
• W4287958190 hasBestOaLocation W42879581901 @default.
• W4287958190 hasConcept C119857082 @default.
• W4287958190 hasConcept C134306372 @default.
• W4287958190 hasConcept C140331021 @default.
• W4287958190 hasConcept C153180895 @default.
• W4287958190 hasConcept C154945302 @default.
• W4287958190 hasConcept C19118579 @default.
• W4287958190 hasConcept C205372480 @default.
• W4287958190 hasConcept C2781238097 @default.
• W4287958190 hasConcept C31972630 @default.
• W4287958190 hasConcept C33923547 @default.
• W4287958190 hasConcept C36503486 @default.
• W4287958190 hasConcept C41008148 @default.
• W4287958190 hasConcept C45347329 @default.
• W4287958190 hasConcept C50644808 @default.
• W4287958190 hasConcept C52622490 @default.
• W4287958190 hasConcept C61272859 @default.
• W4287958190 hasConcept C81363708 @default.
• W4287958190 hasConcept C89600930 @default.
• W4287958190 hasConceptScore W4287958190C119857082 @default.
• W4287958190 hasConceptScore W4287958190C134306372 @default.
• W4287958190 hasConceptScore W4287958190C140331021 @default.
• W4287958190 hasConceptScore W4287958190C153180895 @default.
• W4287958190 hasConceptScore W4287958190C154945302 @default.
• W4287958190 hasConceptScore W4287958190C19118579 @default.
• W4287958190 hasConceptScore W4287958190C205372480 @default.
• W4287958190 hasConceptScore W4287958190C2781238097 @default.
• W4287958190 hasConceptScore W4287958190C31972630 @default.
• W4287958190 hasConceptScore W4287958190C33923547 @default.
• W4287958190 hasConceptScore W4287958190C36503486 @default.
• W4287958190 hasConceptScore W4287958190C41008148 @default.
• W4287958190 hasConceptScore W4287958190C45347329 @default.
• W4287958190 hasConceptScore W4287958190C50644808 @default.
• W4287958190 hasConceptScore W4287958190C52622490 @default.
• W4287958190 hasConceptScore W4287958190C61272859 @default.
• W4287958190 hasConceptScore W4287958190C81363708 @default.
• W4287958190 hasConceptScore W4287958190C89600930 @default.
• W4287958190 hasFunder F4320311212 @default.
• W4287958190 hasFunder F4320321001 @default.
• W4287958190 hasFunder F4320321133 @default.
• W4287958190 hasFunder F4320322847 @default.
• W4287958190 hasFunder F4320327278 @default.
• W4287958190 hasLocation W42879581901 @default.
• W4287958190 hasLocation W42879581902 @default.
• W4287958190 hasOpenAccess W4287958190 @default.
• W4287958190 hasPrimaryLocation W42879581901 @default.
• W4287958190 hasRelatedWork W1669643531 @default.

• next