FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3104369000> ?p ?o ?g. }

• W3104369000 abstract "Translating satellite imagery into maps requires intensive effort and time, especially leading to inaccurate maps of the affected regions during disaster and conflict. The combination of availability of recent datasets and advances in computer vision made through deep learning paved the way toward automated satellite image translation. To facilitate research in this direction, we introduce the Satellite Imagery Competition using a modified SpaceNet dataset. Participants had to come up with different segmentation models to detect positions of buildings on satellite images. In this work, we present five approaches based on improvements of U-Net and Mask R-Convolutional Neuronal Networks models, coupled with unique training adaptations using boosting algorithms, morphological filter, Conditional Random Fields and custom losses. The good results—as high as <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=m1><mml:mrow><mml:mi>A</mml:mi><mml:mi>P</mml:mi><mml:mo>=</mml:mo><mml:mn>0.937</mml:mn></mml:mrow></mml:math> and <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=m2><mml:mrow><mml:mi>A</mml:mi><mml:mi>R</mml:mi><mml:mo>=</mml:mo><mml:mn>0.959</mml:mn></mml:mrow></mml:math> —from these models demonstrate the feasibility of Deep Learning in automated satellite image annotation." @default.
• W3104369000 created "2020-11-23" @default.
• W3104369000 creator A5010649096 @default.
• W3104369000 creator A5011169398 @default.
• W3104369000 creator A5011185444 @default.
• W3104369000 creator A5011525000 @default.
• W3104369000 creator A5014785150 @default.
• W3104369000 creator A5022964565 @default.
• W3104369000 creator A5036231894 @default.
• W3104369000 creator A5042605736 @default.
• W3104369000 creator A5045550207 @default.
• W3104369000 creator A5046893125 @default.
• W3104369000 creator A5051350368 @default.
• W3104369000 creator A5055664722 @default.
• W3104369000 creator A5058420080 @default.
• W3104369000 creator A5065866182 @default.
• W3104369000 creator A5068251712 @default.
• W3104369000 creator A5082438627 @default.
• W3104369000 date "2020-11-16" @default.
• W3104369000 modified "2023-10-10" @default.
• W3104369000 title "Deep Learning for Understanding Satellite Imagery: An Experimental Survey" @default.
• W3104369000 cites W2054279472 @default.
• W3104369000 cites W2101926813 @default.
• W3104369000 cites W2412782625 @default.
• W3104369000 cites W2517954747 @default.
• W3104369000 cites W2794948653 @default.
• W3104369000 cites W2806581075 @default.
• W3104369000 cites W2912327653 @default.
• W3104369000 cites W2919115771 @default.
• W3104369000 cites W2962914239 @default.
• W3104369000 cites W2963026768 @default.
• W3104369000 cites W3003359010 @default.
• W3104369000 cites W3016889634 @default.
• W3104369000 cites W3106250896 @default.
• W3104369000 doi "https://doi.org/10.3389/frai.2020.534696" @default.
• W3104369000 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7944145" @default.
• W3104369000 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33733198" @default.
• W3104369000 hasPublicationYear "2020" @default.
• W3104369000 type Work @default.
• W3104369000 sameAs 3104369000 @default.
• W3104369000 citedByCount "33" @default.
• W3104369000 countsByYear W31043690002021 @default.
• W3104369000 countsByYear W31043690002022 @default.
• W3104369000 countsByYear W31043690002023 @default.
• W3104369000 crossrefType "journal-article" @default.
• W3104369000 hasAuthorship W3104369000A5010649096 @default.
• W3104369000 hasAuthorship W3104369000A5011169398 @default.
• W3104369000 hasAuthorship W3104369000A5011185444 @default.
• W3104369000 hasAuthorship W3104369000A5011525000 @default.
• W3104369000 hasAuthorship W3104369000A5014785150 @default.
• W3104369000 hasAuthorship W3104369000A5022964565 @default.
• W3104369000 hasAuthorship W3104369000A5036231894 @default.
• W3104369000 hasAuthorship W3104369000A5042605736 @default.
• W3104369000 hasAuthorship W3104369000A5045550207 @default.
• W3104369000 hasAuthorship W3104369000A5046893125 @default.
• W3104369000 hasAuthorship W3104369000A5051350368 @default.
• W3104369000 hasAuthorship W3104369000A5055664722 @default.
• W3104369000 hasAuthorship W3104369000A5058420080 @default.
• W3104369000 hasAuthorship W3104369000A5065866182 @default.
• W3104369000 hasAuthorship W3104369000A5068251712 @default.
• W3104369000 hasAuthorship W3104369000A5082438627 @default.
• W3104369000 hasBestOaLocation W31043690001 @default.
• W3104369000 hasConcept C108583219 @default.
• W3104369000 hasConcept C11413529 @default.
• W3104369000 hasConcept C119857082 @default.
• W3104369000 hasConcept C121332964 @default.
• W3104369000 hasConcept C127313418 @default.
• W3104369000 hasConcept C1276947 @default.
• W3104369000 hasConcept C154945302 @default.
• W3104369000 hasConcept C19269812 @default.
• W3104369000 hasConcept C2778102629 @default.
• W3104369000 hasConcept C41008148 @default.
• W3104369000 hasConcept C62649853 @default.
• W3104369000 hasConceptScore W3104369000C108583219 @default.
• W3104369000 hasConceptScore W3104369000C11413529 @default.
• W3104369000 hasConceptScore W3104369000C119857082 @default.
• W3104369000 hasConceptScore W3104369000C121332964 @default.
• W3104369000 hasConceptScore W3104369000C127313418 @default.
• W3104369000 hasConceptScore W3104369000C1276947 @default.
• W3104369000 hasConceptScore W3104369000C154945302 @default.
• W3104369000 hasConceptScore W3104369000C19269812 @default.
• W3104369000 hasConceptScore W3104369000C2778102629 @default.
• W3104369000 hasConceptScore W3104369000C41008148 @default.
• W3104369000 hasConceptScore W3104369000C62649853 @default.
• W3104369000 hasLocation W31043690001 @default.
• W3104369000 hasLocation W31043690002 @default.
• W3104369000 hasLocation W31043690003 @default.
• W3104369000 hasLocation W31043690004 @default.
• W3104369000 hasLocation W31043690005 @default.
• W3104369000 hasOpenAccess W3104369000 @default.
• W3104369000 hasPrimaryLocation W31043690001 @default.
• W3104369000 hasRelatedWork W2922457425 @default.
• W3104369000 hasRelatedWork W3014300295 @default.
• W3104369000 hasRelatedWork W3124051732 @default.
• W3104369000 hasRelatedWork W3164822677 @default.
• W3104369000 hasRelatedWork W3215138031 @default.
• W3104369000 hasRelatedWork W4223943233 @default.
• W3104369000 hasRelatedWork W4225161397 @default.
• W3104369000 hasRelatedWork W4250304930 @default.
• W3104369000 hasRelatedWork W4299487748 @default.

• next