FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136393638> ?p ?o ?g. }

• W3136393638 endingPage "1049" @default.
• W3136393638 startingPage "1049" @default.
• W3136393638 abstract "Most of the existing approaches to the extraction of buildings from high-resolution orthoimages consider the problem as semantic segmentation, which extracts a pixel-wise mask for buildings and trains end-to-end with manually labeled building maps. However, as buildings are highly structured, such a strategy suffers several problems, such as blurred boundaries and the adhesion to close objects. To alleviate the above problems, we proposed a new strategy that also considers the contours of the buildings. Both the contours and structures of the buildings are jointly learned in the same network. The contours are learnable because the boundary of the mask labels of buildings implicitly represents the contours of buildings. We utilized the building contour information embedded in the labels to optimize the representation of building boundaries, then combined the contour information with multi-scale semantic features to enhance the robustness to image spatial resolution. The experimental results showed that the proposed method achieved 91.64%, 81.34%, and 74.51% intersection over union (IoU) on the WHU, Aerial, and Massachusetts building datasets, and outperformed the state-of-the-art (SOTA) methods. It significantly improved the accuracy of building boundaries, especially for the edges of adjacent buildings. The code is made publicly available." @default.
• W3136393638 created "2021-03-29" @default.
• W3136393638 creator A5012718640 @default.
• W3136393638 creator A5041512805 @default.
• W3136393638 creator A5046744673 @default.
• W3136393638 creator A5050209085 @default.
• W3136393638 creator A5051244038 @default.
• W3136393638 creator A5060749423 @default.
• W3136393638 creator A5091049278 @default.
• W3136393638 date "2021-03-10" @default.
• W3136393638 modified "2023-10-16" @default.
• W3136393638 title "Joint Learning of Contour and Structure for Boundary-Preserved Building Extraction" @default.
• W3136393638 cites W1976827068 @default.
• W3136393638 cites W2000803298 @default.
• W3136393638 cites W2018839022 @default.
• W3136393638 cites W2141422564 @default.
• W3136393638 cites W2284448692 @default.
• W3136393638 cites W2412782625 @default.
• W3136393638 cites W2503140068 @default.
• W3136393638 cites W2620689612 @default.
• W3136393638 cites W2623490820 @default.
• W3136393638 cites W2757094569 @default.
• W3136393638 cites W2760340275 @default.
• W3136393638 cites W2787614951 @default.
• W3136393638 cites W2790741584 @default.
• W3136393638 cites W2809426059 @default.
• W3136393638 cites W2888733778 @default.
• W3136393638 cites W2888889084 @default.
• W3136393638 cites W2889301062 @default.
• W3136393638 cites W2897936062 @default.
• W3136393638 cites W2900629394 @default.
• W3136393638 cites W2908320224 @default.
• W3136393638 cites W2911375751 @default.
• W3136393638 cites W2912114399 @default.
• W3136393638 cites W2939647427 @default.
• W3136393638 cites W2962783501 @default.
• W3136393638 cites W2963570197 @default.
• W3136393638 cites W2963659230 @default.
• W3136393638 cites W2980346985 @default.
• W3136393638 cites W2982206001 @default.
• W3136393638 cites W2991441757 @default.
• W3136393638 cites W2994342516 @default.
• W3136393638 cites W2996327453 @default.
• W3136393638 cites W3005428246 @default.
• W3136393638 cites W3007268491 @default.
• W3136393638 cites W3009974559 @default.
• W3136393638 cites W3012630451 @default.
• W3136393638 cites W3014060899 @default.
• W3136393638 cites W3019847943 @default.
• W3136393638 cites W3022397457 @default.
• W3136393638 cites W3024506755 @default.
• W3136393638 cites W3033755576 @default.
• W3136393638 cites W3035752277 @default.
• W3136393638 cites W3038206524 @default.
• W3136393638 cites W3083786945 @default.
• W3136393638 cites W3103294501 @default.
• W3136393638 cites W3112979587 @default.
• W3136393638 doi "https://doi.org/10.3390/rs13061049" @default.
• W3136393638 hasPublicationYear "2021" @default.
• W3136393638 type Work @default.
• W3136393638 sameAs 3136393638 @default.
• W3136393638 citedByCount "28" @default.
• W3136393638 countsByYear W31363936382021 @default.
• W3136393638 countsByYear W31363936382022 @default.
• W3136393638 countsByYear W31363936382023 @default.
• W3136393638 crossrefType "journal-article" @default.
• W3136393638 hasAuthorship W3136393638A5012718640 @default.
• W3136393638 hasAuthorship W3136393638A5041512805 @default.
• W3136393638 hasAuthorship W3136393638A5046744673 @default.
• W3136393638 hasAuthorship W3136393638A5050209085 @default.
• W3136393638 hasAuthorship W3136393638A5051244038 @default.
• W3136393638 hasAuthorship W3136393638A5060749423 @default.
• W3136393638 hasAuthorship W3136393638A5091049278 @default.
• W3136393638 hasBestOaLocation W31363936381 @default.
• W3136393638 hasConcept C104317684 @default.
• W3136393638 hasConcept C115961682 @default.
• W3136393638 hasConcept C127413603 @default.
• W3136393638 hasConcept C134306372 @default.
• W3136393638 hasConcept C154945302 @default.
• W3136393638 hasConcept C170154142 @default.
• W3136393638 hasConcept C18555067 @default.
• W3136393638 hasConcept C185592680 @default.
• W3136393638 hasConcept C2776429412 @default.
• W3136393638 hasConcept C31972630 @default.
• W3136393638 hasConcept C33923547 @default.
• W3136393638 hasConcept C41008148 @default.
• W3136393638 hasConcept C55493867 @default.
• W3136393638 hasConcept C62354387 @default.
• W3136393638 hasConcept C63479239 @default.
• W3136393638 hasConcept C89600930 @default.
• W3136393638 hasConceptScore W3136393638C104317684 @default.
• W3136393638 hasConceptScore W3136393638C115961682 @default.
• W3136393638 hasConceptScore W3136393638C127413603 @default.
• W3136393638 hasConceptScore W3136393638C134306372 @default.
• W3136393638 hasConceptScore W3136393638C154945302 @default.
• W3136393638 hasConceptScore W3136393638C170154142 @default.
• W3136393638 hasConceptScore W3136393638C18555067 @default.
• W3136393638 hasConceptScore W3136393638C185592680 @default.

• next