Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159442990> ?p ?o ?g. }
- W3159442990 endingPage "64392" @default.
- W3159442990 startingPage "64381" @default.
- W3159442990 abstract "Road network extraction from remotely sensed imagery has become a powerful tool for updating geospatial databases, owing to the success of convolutional neural network (CNN) based deep learning semantic segmentation techniques combined with the high-resolution imagery that modern remote sensing provides. However, most CNN approaches cannot obtain high precision segmentation maps with rich details when processing high-resolution remote sensing imagery. In this study, we propose a generative adversarial network (GAN)-based deep learning approach for road segmentation from high-resolution aerial imagery. In the generative part of the presented GAN approach, we use a modified UNet model (MUNet) to obtain a high-resolution segmentation map of the road network. In combination with simple pre-processing comprising edge-preserving filtering, the proposed approach offers a significant improvement in road network segmentation compared with prior approaches. In experiments conducted on the Massachusetts road image dataset, the proposed approach achieves 91.54% precision and 92.92% recall, which correspond to a Mathews correlation coefficient (MCC) of 91.13%, a Mean intersection over union (MIOU) of 87.43% and a F1-score of 92.20%. Comparisons demonstrate that the proposed GAN framework outperforms prior CNN-based approaches and is particularly effective in preserving edge information." @default.
- W3159442990 created "2021-05-10" @default.
- W3159442990 creator A5028417716 @default.
- W3159442990 creator A5029739578 @default.
- W3159442990 creator A5051876605 @default.
- W3159442990 creator A5059040421 @default.
- W3159442990 creator A5061766375 @default.
- W3159442990 date "2021-01-01" @default.
- W3159442990 modified "2023-09-30" @default.
- W3159442990 title "Improving Road Semantic Segmentation Using Generative Adversarial Network" @default.
- W3159442990 cites W1535289548 @default.
- W3159442990 cites W1903029394 @default.
- W3159442990 cites W1974097572 @default.
- W3159442990 cites W1987497606 @default.
- W3159442990 cites W1993465480 @default.
- W3159442990 cites W2022902702 @default.
- W3159442990 cites W2112725765 @default.
- W3159442990 cites W2161790807 @default.
- W3159442990 cites W2308318555 @default.
- W3159442990 cites W2395811491 @default.
- W3159442990 cites W2546821789 @default.
- W3159442990 cites W2547880720 @default.
- W3159442990 cites W2593886839 @default.
- W3159442990 cites W2594203750 @default.
- W3159442990 cites W2595659188 @default.
- W3159442990 cites W2595964094 @default.
- W3159442990 cites W2758247951 @default.
- W3159442990 cites W2766624546 @default.
- W3159442990 cites W2768705966 @default.
- W3159442990 cites W2786492053 @default.
- W3159442990 cites W2789330112 @default.
- W3159442990 cites W2889009110 @default.
- W3159442990 cites W2890554434 @default.
- W3159442990 cites W2891367133 @default.
- W3159442990 cites W2903224593 @default.
- W3159442990 cites W2909646705 @default.
- W3159442990 cites W2919627848 @default.
- W3159442990 cites W2921476973 @default.
- W3159442990 cites W2923594733 @default.
- W3159442990 cites W2938004456 @default.
- W3159442990 cites W2943153115 @default.
- W3159442990 cites W2962978395 @default.
- W3159442990 cites W3005521100 @default.
- W3159442990 cites W3021297918 @default.
- W3159442990 cites W3025407686 @default.
- W3159442990 cites W3068105938 @default.
- W3159442990 cites W3087899141 @default.
- W3159442990 cites W3088134661 @default.
- W3159442990 cites W3093892353 @default.
- W3159442990 cites W3096044153 @default.
- W3159442990 cites W3099113392 @default.
- W3159442990 cites W3136215587 @default.
- W3159442990 doi "https://doi.org/10.1109/access.2021.3075951" @default.
- W3159442990 hasPublicationYear "2021" @default.
- W3159442990 type Work @default.
- W3159442990 sameAs 3159442990 @default.
- W3159442990 citedByCount "30" @default.
- W3159442990 countsByYear W31594429902021 @default.
- W3159442990 countsByYear W31594429902022 @default.
- W3159442990 countsByYear W31594429902023 @default.
- W3159442990 crossrefType "journal-article" @default.
- W3159442990 hasAuthorship W3159442990A5028417716 @default.
- W3159442990 hasAuthorship W3159442990A5029739578 @default.
- W3159442990 hasAuthorship W3159442990A5051876605 @default.
- W3159442990 hasAuthorship W3159442990A5059040421 @default.
- W3159442990 hasAuthorship W3159442990A5061766375 @default.
- W3159442990 hasBestOaLocation W31594429901 @default.
- W3159442990 hasConcept C108583219 @default.
- W3159442990 hasConcept C124504099 @default.
- W3159442990 hasConcept C153180895 @default.
- W3159442990 hasConcept C154945302 @default.
- W3159442990 hasConcept C162307627 @default.
- W3159442990 hasConcept C205649164 @default.
- W3159442990 hasConcept C31972630 @default.
- W3159442990 hasConcept C41008148 @default.
- W3159442990 hasConcept C58640448 @default.
- W3159442990 hasConcept C64543145 @default.
- W3159442990 hasConcept C81363708 @default.
- W3159442990 hasConcept C89600930 @default.
- W3159442990 hasConceptScore W3159442990C108583219 @default.
- W3159442990 hasConceptScore W3159442990C124504099 @default.
- W3159442990 hasConceptScore W3159442990C153180895 @default.
- W3159442990 hasConceptScore W3159442990C154945302 @default.
- W3159442990 hasConceptScore W3159442990C162307627 @default.
- W3159442990 hasConceptScore W3159442990C205649164 @default.
- W3159442990 hasConceptScore W3159442990C31972630 @default.
- W3159442990 hasConceptScore W3159442990C41008148 @default.
- W3159442990 hasConceptScore W3159442990C58640448 @default.
- W3159442990 hasConceptScore W3159442990C64543145 @default.
- W3159442990 hasConceptScore W3159442990C81363708 @default.
- W3159442990 hasConceptScore W3159442990C89600930 @default.
- W3159442990 hasFunder F4320320967 @default.
- W3159442990 hasFunder F4320321145 @default.
- W3159442990 hasFunder F4320322699 @default.
- W3159442990 hasLocation W31594429901 @default.
- W3159442990 hasLocation W31594429902 @default.
- W3159442990 hasLocation W31594429903 @default.
- W3159442990 hasOpenAccess W3159442990 @default.