Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134927667> ?p ?o ?g. }
- W3134927667 endingPage "12" @default.
- W3134927667 startingPage "1" @default.
- W3134927667 abstract "Road surface extraction from remote sensing images using deep learning methods has achieved good performance, while most of the existing methods are based on fully supervised learning, which requires a large amount of training data with laborious per-pixel annotation. In this article, we propose a scribble-based weakly supervised road surface extraction method named ScRoadExtractor, which learns from easily accessible scribbles such as centerlines instead of densely annotated road surface ground truths. To propagate semantic information from sparse scribbles to unlabeled pixels, we introduce a road label propagation algorithm, which considers both the buffer-based properties of road networks and the color and spatial information of super-pixels, to produce a proposal mask with categories road, nonroad, and unknown. The proposal mask, along with the auxiliary boundary prior information detected from images, is utilized to train a dual-branch encoder–decoder network which we designed for precise road surface segmentation. We perform experiments on three diverse road data sets that are comprised of high-resolution remote sensing satellite and aerial images across the world. The results demonstrate that ScRoadExtractor exceeds the classic scribble-supervised segmentation method by 20% for the intersection over union (IoU) indicator and outperforms the state-of-the-art scribble-based weakly supervised methods at least 4%." @default.
- W3134927667 created "2021-03-15" @default.
- W3134927667 creator A5031588692 @default.
- W3134927667 creator A5071892663 @default.
- W3134927667 date "2022-01-01" @default.
- W3134927667 modified "2023-10-16" @default.
- W3134927667 title "Scribble-Based Weakly Supervised Deep Learning for Road Surface Extraction From Remote Sensing Images" @default.
- W3134927667 cites W1495267108 @default.
- W3134927667 cites W1837697898 @default.
- W3134927667 cites W1927251054 @default.
- W3134927667 cites W1964772475 @default.
- W3134927667 cites W1976159359 @default.
- W3134927667 cites W1984288883 @default.
- W3134927667 cites W1989750313 @default.
- W3134927667 cites W2050560048 @default.
- W3134927667 cites W2110158442 @default.
- W3134927667 cites W2113137767 @default.
- W3134927667 cites W2117539524 @default.
- W3134927667 cites W2118246710 @default.
- W3134927667 cites W2141200610 @default.
- W3134927667 cites W2143516773 @default.
- W3134927667 cites W2145023731 @default.
- W3134927667 cites W2155226776 @default.
- W3134927667 cites W2194775991 @default.
- W3134927667 cites W2205800717 @default.
- W3134927667 cites W2221898772 @default.
- W3134927667 cites W2306289963 @default.
- W3134927667 cites W2337429362 @default.
- W3134927667 cites W2412782625 @default.
- W3134927667 cites W2552414813 @default.
- W3134927667 cites W2593886839 @default.
- W3134927667 cites W2594203750 @default.
- W3134927667 cites W2620899671 @default.
- W3134927667 cites W2774320778 @default.
- W3134927667 cites W2798925380 @default.
- W3134927667 cites W2804199516 @default.
- W3134927667 cites W2806808924 @default.
- W3134927667 cites W2890554434 @default.
- W3134927667 cites W2893801697 @default.
- W3134927667 cites W2938004456 @default.
- W3134927667 cites W2943295486 @default.
- W3134927667 cites W2962758679 @default.
- W3134927667 cites W2963198662 @default.
- W3134927667 cites W2963446712 @default.
- W3134927667 cites W2963687373 @default.
- W3134927667 cites W2963881378 @default.
- W3134927667 cites W2966037847 @default.
- W3134927667 cites W2981329832 @default.
- W3134927667 cites W2982628450 @default.
- W3134927667 cites W2992559558 @default.
- W3134927667 cites W3024167159 @default.
- W3134927667 cites W3034453930 @default.
- W3134927667 cites W3100040694 @default.
- W3134927667 cites W3100521496 @default.
- W3134927667 cites W73112891 @default.
- W3134927667 cites W845365781 @default.
- W3134927667 doi "https://doi.org/10.1109/tgrs.2021.3061213" @default.
- W3134927667 hasPublicationYear "2022" @default.
- W3134927667 type Work @default.
- W3134927667 sameAs 3134927667 @default.
- W3134927667 citedByCount "17" @default.
- W3134927667 countsByYear W31349276672021 @default.
- W3134927667 countsByYear W31349276672022 @default.
- W3134927667 countsByYear W31349276672023 @default.
- W3134927667 crossrefType "journal-article" @default.
- W3134927667 hasAuthorship W3134927667A5031588692 @default.
- W3134927667 hasAuthorship W3134927667A5071892663 @default.
- W3134927667 hasBestOaLocation W31349276672 @default.
- W3134927667 hasConcept C108583219 @default.
- W3134927667 hasConcept C124504099 @default.
- W3134927667 hasConcept C127313418 @default.
- W3134927667 hasConcept C134306372 @default.
- W3134927667 hasConcept C136389625 @default.
- W3134927667 hasConcept C146849305 @default.
- W3134927667 hasConcept C153180895 @default.
- W3134927667 hasConcept C154945302 @default.
- W3134927667 hasConcept C160633673 @default.
- W3134927667 hasConcept C205649164 @default.
- W3134927667 hasConcept C31972630 @default.
- W3134927667 hasConcept C33923547 @default.
- W3134927667 hasConcept C41008148 @default.
- W3134927667 hasConcept C50644808 @default.
- W3134927667 hasConcept C58640448 @default.
- W3134927667 hasConcept C62354387 @default.
- W3134927667 hasConcept C62649853 @default.
- W3134927667 hasConcept C64543145 @default.
- W3134927667 hasConcept C89600930 @default.
- W3134927667 hasConceptScore W3134927667C108583219 @default.
- W3134927667 hasConceptScore W3134927667C124504099 @default.
- W3134927667 hasConceptScore W3134927667C127313418 @default.
- W3134927667 hasConceptScore W3134927667C134306372 @default.
- W3134927667 hasConceptScore W3134927667C136389625 @default.
- W3134927667 hasConceptScore W3134927667C146849305 @default.
- W3134927667 hasConceptScore W3134927667C153180895 @default.
- W3134927667 hasConceptScore W3134927667C154945302 @default.
- W3134927667 hasConceptScore W3134927667C160633673 @default.
- W3134927667 hasConceptScore W3134927667C205649164 @default.
- W3134927667 hasConceptScore W3134927667C31972630 @default.