Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280491130> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4280491130 endingPage "2422" @default.
- W4280491130 startingPage "2422" @default.
- W4280491130 abstract "At present, road continuity is a major challenge, and it is difficult to extract the centerline vector of roads, especially when the road view is obstructed by trees or other structures. Most of the existing research has focused on optimizing the available deep-learning networks. However, the segmentation accuracy is also affected by the loss function. Currently, little research has been published on road segmentation loss functions. To resolve this problem, an attention loss function named GapLoss that can be combined with any segmentation network was proposed. Firstly, a deep-learning network was used to obtain a binary prediction mask. Secondly, a vector skeleton was extracted from the prediction mask. Thirdly, for each pixel, eight neighboring pixels with the same value of the pixel were calculated. If the value was 1, then the pixel was identified as the endpoint. Fourth, according to the number of endpoints within a buffered range, each pixel in the prediction image was given a corresponding weight. Finally, the weighted average value of the cross-entropy of all the pixels in the batch was used as the final loss function value. We employed four well-known semantic segmentation networks to conduct comparative experiments on three large datasets. The results showed that, compared to other loss functions, the evaluation metrics after using GapLoss were nearly all improved. From the predicted image, the road prediction by GapLoss was more continuous, especially at intersections and when the road was obscured from view, and the road segmentation accuracy was improved." @default.
- W4280491130 created "2022-05-22" @default.
- W4280491130 creator A5059389072 @default.
- W4280491130 creator A5090740844 @default.
- W4280491130 date "2022-05-18" @default.
- W4280491130 modified "2023-10-18" @default.
- W4280491130 title "GapLoss: A Loss Function for Semantic Segmentation of Roads in Remote Sensing Images" @default.
- W4280491130 cites W1536729381 @default.
- W4280491130 cites W2022902702 @default.
- W4280491130 cites W2101608218 @default.
- W4280491130 cites W2144572173 @default.
- W4280491130 cites W2412782625 @default.
- W4280491130 cites W2547880720 @default.
- W4280491130 cites W2560023338 @default.
- W4280491130 cites W2566121015 @default.
- W4280491130 cites W2595964094 @default.
- W4280491130 cites W2774320778 @default.
- W4280491130 cites W2780861787 @default.
- W4280491130 cites W2789330112 @default.
- W4280491130 cites W2884281986 @default.
- W4280491130 cites W2884561390 @default.
- W4280491130 cites W2890554434 @default.
- W4280491130 cites W2911964244 @default.
- W4280491130 cites W2962914239 @default.
- W4280491130 cites W2963881378 @default.
- W4280491130 cites W2975194617 @default.
- W4280491130 cites W2981329832 @default.
- W4280491130 cites W2996290406 @default.
- W4280491130 cites W3015281476 @default.
- W4280491130 cites W3034985049 @default.
- W4280491130 cites W3046474724 @default.
- W4280491130 cites W3100521496 @default.
- W4280491130 cites W3112139896 @default.
- W4280491130 cites W3164563478 @default.
- W4280491130 cites W4233497883 @default.
- W4280491130 doi "https://doi.org/10.3390/rs14102422" @default.
- W4280491130 hasPublicationYear "2022" @default.
- W4280491130 type Work @default.
- W4280491130 citedByCount "3" @default.
- W4280491130 countsByYear W42804911302022 @default.
- W4280491130 countsByYear W42804911302023 @default.
- W4280491130 crossrefType "journal-article" @default.
- W4280491130 hasAuthorship W4280491130A5059389072 @default.
- W4280491130 hasAuthorship W4280491130A5090740844 @default.
- W4280491130 hasBestOaLocation W42804911301 @default.
- W4280491130 hasConcept C124504099 @default.
- W4280491130 hasConcept C153180895 @default.
- W4280491130 hasConcept C154945302 @default.
- W4280491130 hasConcept C160633673 @default.
- W4280491130 hasConcept C2524010 @default.
- W4280491130 hasConcept C28719098 @default.
- W4280491130 hasConcept C31972630 @default.
- W4280491130 hasConcept C33923547 @default.
- W4280491130 hasConcept C41008148 @default.
- W4280491130 hasConcept C89600930 @default.
- W4280491130 hasConceptScore W4280491130C124504099 @default.
- W4280491130 hasConceptScore W4280491130C153180895 @default.
- W4280491130 hasConceptScore W4280491130C154945302 @default.
- W4280491130 hasConceptScore W4280491130C160633673 @default.
- W4280491130 hasConceptScore W4280491130C2524010 @default.
- W4280491130 hasConceptScore W4280491130C28719098 @default.
- W4280491130 hasConceptScore W4280491130C31972630 @default.
- W4280491130 hasConceptScore W4280491130C33923547 @default.
- W4280491130 hasConceptScore W4280491130C41008148 @default.
- W4280491130 hasConceptScore W4280491130C89600930 @default.
- W4280491130 hasIssue "10" @default.
- W4280491130 hasLocation W42804911301 @default.
- W4280491130 hasLocation W42804911302 @default.
- W4280491130 hasOpenAccess W4280491130 @default.
- W4280491130 hasPrimaryLocation W42804911301 @default.
- W4280491130 hasRelatedWork W121273120 @default.
- W4280491130 hasRelatedWork W1669643531 @default.
- W4280491130 hasRelatedWork W2005437358 @default.
- W4280491130 hasRelatedWork W2008656436 @default.
- W4280491130 hasRelatedWork W2023558673 @default.
- W4280491130 hasRelatedWork W2134924024 @default.
- W4280491130 hasRelatedWork W2337415362 @default.
- W4280491130 hasRelatedWork W2517104666 @default.
- W4280491130 hasRelatedWork W2740820121 @default.
- W4280491130 hasRelatedWork W4312857205 @default.
- W4280491130 hasVolume "14" @default.
- W4280491130 isParatext "false" @default.
- W4280491130 isRetracted "false" @default.
- W4280491130 workType "article" @default.