Matches in SemOpenAlex for { <https://semopenalex.org/work/W3085020121> ?p ?o ?g. }
- W3085020121 abstract "Abstract The semantic segmentation of remotely sensed aerial imagery is nowadays an extensively explored task, concerned with determining, for each pixel in an input image, the most likely class label from a finite set of possible labels. Most previous work in the area has addressed the analysis of high‐resolution modern images, although the semantic segmentation of historical grayscale aerial photos can also have important applications. Examples include supporting the development of historical road maps, or the development of dasymetric disaggregation approaches leveraging historical building footprints. Following recent work in the area related to the use of fully‐convolutional neural networks for semantic segmentation, and specifically envisioning the segmentation of grayscale aerial imagery, we evaluated the performance of an adapted version of the W‐Net architecture, which has achieved very good results on other types of image segmentation tasks. Our W‐Net model is trained to simultaneously segment images and reconstruct, or predict, the colour of the input images from intermediate representations. Through experiments with distinct data sets frequently used in previous studies, we show that the proposed W‐Net architecture is quite effective in colouring and segmenting the input images. The proposed approach outperforms a baseline corresponding to the U‐Net model for the segmentation of both coloured and grayscale imagery, and it also outperforms some of the other recently proposed approaches when considering coloured imagery." @default.
- W3085020121 created "2020-09-21" @default.
- W3085020121 creator A5042283153 @default.
- W3085020121 creator A5049321280 @default.
- W3085020121 creator A5055101594 @default.
- W3085020121 creator A5055392122 @default.
- W3085020121 creator A5090994567 @default.
- W3085020121 date "2020-09-08" @default.
- W3085020121 modified "2023-10-16" @default.
- W3085020121 title "Semantic segmentation and colorization of grayscale aerial imagery with <scp>W‐Net</scp> models" @default.
- W3085020121 cites W1569176441 @default.
- W3085020121 cites W1849277567 @default.
- W3085020121 cites W1901129140 @default.
- W3085020121 cites W1903029394 @default.
- W3085020121 cites W1915485278 @default.
- W3085020121 cites W2036304176 @default.
- W3085020121 cites W2037028543 @default.
- W3085020121 cites W2040956387 @default.
- W3085020121 cites W2120957161 @default.
- W3085020121 cites W2121947440 @default.
- W3085020121 cites W2194775991 @default.
- W3085020121 cites W2307770531 @default.
- W3085020121 cites W2559597482 @default.
- W3085020121 cites W2734349601 @default.
- W3085020121 cites W2774320778 @default.
- W3085020121 cites W2778539913 @default.
- W3085020121 cites W2793461576 @default.
- W3085020121 cites W2794948653 @default.
- W3085020121 cites W2814568980 @default.
- W3085020121 cites W2885151000 @default.
- W3085020121 cites W2885734264 @default.
- W3085020121 cites W2900680440 @default.
- W3085020121 cites W2921778232 @default.
- W3085020121 cites W2945528352 @default.
- W3085020121 cites W2952331051 @default.
- W3085020121 cites W2954156245 @default.
- W3085020121 cites W2963446712 @default.
- W3085020121 cites W2963563573 @default.
- W3085020121 cites W2963881378 @default.
- W3085020121 cites W2963995737 @default.
- W3085020121 cites W2964054038 @default.
- W3085020121 cites W2964227007 @default.
- W3085020121 cites W2965455938 @default.
- W3085020121 cites W2971437404 @default.
- W3085020121 cites W2979553087 @default.
- W3085020121 cites W2984996550 @default.
- W3085020121 cites W2988102470 @default.
- W3085020121 cites W2995009671 @default.
- W3085020121 cites W3028962016 @default.
- W3085020121 doi "https://doi.org/10.1111/exsy.12622" @default.
- W3085020121 hasPublicationYear "2020" @default.
- W3085020121 type Work @default.
- W3085020121 sameAs 3085020121 @default.
- W3085020121 citedByCount "5" @default.
- W3085020121 countsByYear W30850201212020 @default.
- W3085020121 countsByYear W30850201212021 @default.
- W3085020121 countsByYear W30850201212022 @default.
- W3085020121 countsByYear W30850201212023 @default.
- W3085020121 crossrefType "journal-article" @default.
- W3085020121 hasAuthorship W3085020121A5042283153 @default.
- W3085020121 hasAuthorship W3085020121A5049321280 @default.
- W3085020121 hasAuthorship W3085020121A5055101594 @default.
- W3085020121 hasAuthorship W3085020121A5055392122 @default.
- W3085020121 hasAuthorship W3085020121A5090994567 @default.
- W3085020121 hasConcept C124504099 @default.
- W3085020121 hasConcept C153180895 @default.
- W3085020121 hasConcept C154945302 @default.
- W3085020121 hasConcept C160633673 @default.
- W3085020121 hasConcept C31972630 @default.
- W3085020121 hasConcept C41008148 @default.
- W3085020121 hasConcept C78201319 @default.
- W3085020121 hasConcept C81363708 @default.
- W3085020121 hasConcept C89600930 @default.
- W3085020121 hasConceptScore W3085020121C124504099 @default.
- W3085020121 hasConceptScore W3085020121C153180895 @default.
- W3085020121 hasConceptScore W3085020121C154945302 @default.
- W3085020121 hasConceptScore W3085020121C160633673 @default.
- W3085020121 hasConceptScore W3085020121C31972630 @default.
- W3085020121 hasConceptScore W3085020121C41008148 @default.
- W3085020121 hasConceptScore W3085020121C78201319 @default.
- W3085020121 hasConceptScore W3085020121C81363708 @default.
- W3085020121 hasConceptScore W3085020121C89600930 @default.
- W3085020121 hasFunder F4320334779 @default.
- W3085020121 hasIssue "6" @default.
- W3085020121 hasLocation W30850201211 @default.
- W3085020121 hasOpenAccess W3085020121 @default.
- W3085020121 hasPrimaryLocation W30850201211 @default.
- W3085020121 hasRelatedWork W1669643531 @default.
- W3085020121 hasRelatedWork W1970920482 @default.
- W3085020121 hasRelatedWork W2005437358 @default.
- W3085020121 hasRelatedWork W2060518359 @default.
- W3085020121 hasRelatedWork W2147943677 @default.
- W3085020121 hasRelatedWork W2157071234 @default.
- W3085020121 hasRelatedWork W2371329095 @default.
- W3085020121 hasRelatedWork W2433461236 @default.
- W3085020121 hasRelatedWork W2517104666 @default.
- W3085020121 hasRelatedWork W2791049537 @default.
- W3085020121 hasVolume "37" @default.
- W3085020121 isParatext "false" @default.
- W3085020121 isRetracted "false" @default.