Matches in SemOpenAlex for { <https://semopenalex.org/work/W3193128306> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3193128306 endingPage "505" @default.
- W3193128306 startingPage "494" @default.
- W3193128306 abstract "Automatic building extraction has significant socio-economic applications such as population estimation, urban planning, rapid disaster response, monitoring illegal land acquisition, and change detection. The traditional methods fail to deal with the challenges entirely associated with building extraction, i.e. different shape, size, texture of buildings, missing and incomplete buildings due to the occlusion, and high intra-class variation. The existing CNN-based approaches are incapable of recovering the boundary information, especially when the building structures are small and complex. To alleviate the issues faced by current methods, we propose a lightweight attention mechanism-based model – refined cross attention neural network (RCA-Net) for precisely extracting the coarse-to-fine building features. Unlike recent attention mechanism-based approaches, the RCA-Net utilizes spatial and channel attention to capture the long-range multi-scale context. Then, we introduce an efficient attention module, the Global Attention Fuse (GAF) module, that fuses the local and global cross-channel relationships to capture the essential features without enhancing the computational complexity. A loss function, unified loss, is also presented that combines BCE loss and dice loss to alleviate the imbalanced class distribution problem. Experimental results show that our proposed method outperforms the latest method DSNet by 2.06% and 1.47% in IoU and 2.11% and 1.27% in F1-score on the publicly available datasets: Massachusetts building dataset and Inria Aerial Image Labeling dataset, respectively." @default.
- W3193128306 created "2021-08-16" @default.
- W3193128306 creator A5034976097 @default.
- W3193128306 creator A5037033692 @default.
- W3193128306 date "2021-07-30" @default.
- W3193128306 modified "2023-10-16" @default.
- W3193128306 title "Extracting Building Footprints from High-resolution Aerial Imagery Using Refined Cross AttentionNet" @default.
- W3193128306 cites W2194775991 @default.
- W3193128306 cites W2609402060 @default.
- W3193128306 cites W2752782242 @default.
- W3193128306 cites W2888733778 @default.
- W3193128306 cites W2888799854 @default.
- W3193128306 cites W2891222098 @default.
- W3193128306 cites W2897593716 @default.
- W3193128306 cites W2897936062 @default.
- W3193128306 cites W2937933649 @default.
- W3193128306 cites W2939647427 @default.
- W3193128306 cites W2963073398 @default.
- W3193128306 cites W2963091558 @default.
- W3193128306 cites W2963446712 @default.
- W3193128306 cites W2964137095 @default.
- W3193128306 cites W2967087542 @default.
- W3193128306 cites W2971095420 @default.
- W3193128306 cites W2972623730 @default.
- W3193128306 cites W2982206001 @default.
- W3193128306 cites W3000086214 @default.
- W3193128306 cites W3014060899 @default.
- W3193128306 cites W3102850314 @default.
- W3193128306 cites W3112929693 @default.
- W3193128306 cites W3148283428 @default.
- W3193128306 doi "https://doi.org/10.1080/02564602.2021.1955757" @default.
- W3193128306 hasPublicationYear "2021" @default.
- W3193128306 type Work @default.
- W3193128306 sameAs 3193128306 @default.
- W3193128306 citedByCount "2" @default.
- W3193128306 countsByYear W31931283062022 @default.
- W3193128306 crossrefType "journal-article" @default.
- W3193128306 hasAuthorship W3193128306A5034976097 @default.
- W3193128306 hasAuthorship W3193128306A5037033692 @default.
- W3193128306 hasConcept C103278499 @default.
- W3193128306 hasConcept C108583219 @default.
- W3193128306 hasConcept C115961682 @default.
- W3193128306 hasConcept C119599485 @default.
- W3193128306 hasConcept C119857082 @default.
- W3193128306 hasConcept C124101348 @default.
- W3193128306 hasConcept C127162648 @default.
- W3193128306 hasConcept C127413603 @default.
- W3193128306 hasConcept C141353440 @default.
- W3193128306 hasConcept C151730666 @default.
- W3193128306 hasConcept C154945302 @default.
- W3193128306 hasConcept C2776429412 @default.
- W3193128306 hasConcept C2779343474 @default.
- W3193128306 hasConcept C31258907 @default.
- W3193128306 hasConcept C41008148 @default.
- W3193128306 hasConcept C86803240 @default.
- W3193128306 hasConceptScore W3193128306C103278499 @default.
- W3193128306 hasConceptScore W3193128306C108583219 @default.
- W3193128306 hasConceptScore W3193128306C115961682 @default.
- W3193128306 hasConceptScore W3193128306C119599485 @default.
- W3193128306 hasConceptScore W3193128306C119857082 @default.
- W3193128306 hasConceptScore W3193128306C124101348 @default.
- W3193128306 hasConceptScore W3193128306C127162648 @default.
- W3193128306 hasConceptScore W3193128306C127413603 @default.
- W3193128306 hasConceptScore W3193128306C141353440 @default.
- W3193128306 hasConceptScore W3193128306C151730666 @default.
- W3193128306 hasConceptScore W3193128306C154945302 @default.
- W3193128306 hasConceptScore W3193128306C2776429412 @default.
- W3193128306 hasConceptScore W3193128306C2779343474 @default.
- W3193128306 hasConceptScore W3193128306C31258907 @default.
- W3193128306 hasConceptScore W3193128306C41008148 @default.
- W3193128306 hasConceptScore W3193128306C86803240 @default.
- W3193128306 hasIssue "3" @default.
- W3193128306 hasLocation W31931283061 @default.
- W3193128306 hasOpenAccess W3193128306 @default.
- W3193128306 hasPrimaryLocation W31931283061 @default.
- W3193128306 hasRelatedWork W2922457425 @default.
- W3193128306 hasRelatedWork W3014300295 @default.
- W3193128306 hasRelatedWork W3164822677 @default.
- W3193128306 hasRelatedWork W4223943233 @default.
- W3193128306 hasRelatedWork W4225161397 @default.
- W3193128306 hasRelatedWork W4250304930 @default.
- W3193128306 hasRelatedWork W4309045103 @default.
- W3193128306 hasRelatedWork W4312200629 @default.
- W3193128306 hasRelatedWork W4360585206 @default.
- W3193128306 hasRelatedWork W4364306694 @default.
- W3193128306 hasVolume "39" @default.
- W3193128306 isParatext "false" @default.
- W3193128306 isRetracted "false" @default.
- W3193128306 magId "3193128306" @default.
- W3193128306 workType "article" @default.