Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892096486> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2892096486 endingPage "184" @default.
- W2892096486 startingPage "169" @default.
- W2892096486 abstract "Semantic segmentation is an important method to implement fine-grained semantically understand for high-resolution remote sensing images by dividing images into pixel groupings which can then be labelled and classified. In the field of computer vision (CV), the methods based on fully convolutional network (FCN) are the hotspot and have achieved state-of-the-art results. Compared with popular datasets in CV such as PASCAL and COCO, class imbalance is a problem for multiclass semantic segmentation in remote sensing datasets. In this paper, an FCN-based model is proposed to implement pixel-wise classifications for remote sensing image in an end-to-end way, and an adaptive threshold algorithm is proposed to adjust the threshold of Jaccard index in each class. Experiments on DSTL dataset show that the proposed method produces accurate classifications in an end-to-end way. Results show that the adaptive threshold algorithm can increase the score of average Jaccard index from 0.614 to 0.636 and achieve better segmentation results." @default.
- W2892096486 created "2018-09-27" @default.
- W2892096486 creator A5000410753 @default.
- W2892096486 creator A5005994705 @default.
- W2892096486 creator A5008152072 @default.
- W2892096486 creator A5042776708 @default.
- W2892096486 creator A5089331519 @default.
- W2892096486 date "2018-09-06" @default.
- W2892096486 modified "2023-10-14" @default.
- W2892096486 title "Semantic segmentation of high-resolution remote sensing images using fully convolutional network with adaptive threshold" @default.
- W2892096486 cites W2063907334 @default.
- W2892096486 cites W2077312680 @default.
- W2892096486 cites W2085625911 @default.
- W2892096486 cites W2089731186 @default.
- W2892096486 cites W2099577969 @default.
- W2892096486 cites W2117527927 @default.
- W2892096486 cites W2155632266 @default.
- W2892096486 cites W2248723555 @default.
- W2892096486 cites W2308318555 @default.
- W2892096486 cites W2395611524 @default.
- W2892096486 cites W2412588858 @default.
- W2892096486 cites W2412782625 @default.
- W2892096486 cites W2532691318 @default.
- W2892096486 cites W2579318141 @default.
- W2892096486 cites W2595964094 @default.
- W2892096486 cites W2597563280 @default.
- W2892096486 cites W2616755213 @default.
- W2892096486 cites W2618943282 @default.
- W2892096486 cites W2743142445 @default.
- W2892096486 cites W2963881378 @default.
- W2892096486 cites W4253153980 @default.
- W2892096486 doi "https://doi.org/10.1080/09540091.2018.1510902" @default.
- W2892096486 hasPublicationYear "2018" @default.
- W2892096486 type Work @default.
- W2892096486 sameAs 2892096486 @default.
- W2892096486 citedByCount "33" @default.
- W2892096486 countsByYear W28920964862019 @default.
- W2892096486 countsByYear W28920964862020 @default.
- W2892096486 countsByYear W28920964862021 @default.
- W2892096486 countsByYear W28920964862022 @default.
- W2892096486 countsByYear W28920964862023 @default.
- W2892096486 crossrefType "journal-article" @default.
- W2892096486 hasAuthorship W2892096486A5000410753 @default.
- W2892096486 hasAuthorship W2892096486A5005994705 @default.
- W2892096486 hasAuthorship W2892096486A5008152072 @default.
- W2892096486 hasAuthorship W2892096486A5042776708 @default.
- W2892096486 hasAuthorship W2892096486A5089331519 @default.
- W2892096486 hasConcept C124504099 @default.
- W2892096486 hasConcept C153180895 @default.
- W2892096486 hasConcept C154945302 @default.
- W2892096486 hasConcept C160633673 @default.
- W2892096486 hasConcept C199360897 @default.
- W2892096486 hasConcept C203519979 @default.
- W2892096486 hasConcept C41008148 @default.
- W2892096486 hasConcept C75608658 @default.
- W2892096486 hasConcept C81363708 @default.
- W2892096486 hasConcept C89600930 @default.
- W2892096486 hasConceptScore W2892096486C124504099 @default.
- W2892096486 hasConceptScore W2892096486C153180895 @default.
- W2892096486 hasConceptScore W2892096486C154945302 @default.
- W2892096486 hasConceptScore W2892096486C160633673 @default.
- W2892096486 hasConceptScore W2892096486C199360897 @default.
- W2892096486 hasConceptScore W2892096486C203519979 @default.
- W2892096486 hasConceptScore W2892096486C41008148 @default.
- W2892096486 hasConceptScore W2892096486C75608658 @default.
- W2892096486 hasConceptScore W2892096486C81363708 @default.
- W2892096486 hasConceptScore W2892096486C89600930 @default.
- W2892096486 hasIssue "2" @default.
- W2892096486 hasLocation W28920964861 @default.
- W2892096486 hasOpenAccess W2892096486 @default.
- W2892096486 hasPrimaryLocation W28920964861 @default.
- W2892096486 hasRelatedWork W2136485282 @default.
- W2892096486 hasRelatedWork W2424871898 @default.
- W2892096486 hasRelatedWork W2441762250 @default.
- W2892096486 hasRelatedWork W2507402573 @default.
- W2892096486 hasRelatedWork W2546871836 @default.
- W2892096486 hasRelatedWork W2952466432 @default.
- W2892096486 hasRelatedWork W3118494652 @default.
- W2892096486 hasRelatedWork W3135324209 @default.
- W2892096486 hasRelatedWork W4200528772 @default.
- W2892096486 hasRelatedWork W4297914674 @default.
- W2892096486 hasVolume "31" @default.
- W2892096486 isParatext "false" @default.
- W2892096486 isRetracted "false" @default.
- W2892096486 magId "2892096486" @default.
- W2892096486 workType "article" @default.