Matches in SemOpenAlex for { <https://semopenalex.org/work/W2886075188> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2886075188 endingPage "93" @default.
- W2886075188 startingPage "93" @default.
- W2886075188 abstract "Recent breakthroughs in the computer vision community have led to the emergence of efficient deep learning techniques for end-to-end segmentation of natural scenes. Underwater imaging stands to gain from these advances, however, deep learning methods require large annotated datasets for model training and these are typically unavailable for underwater imaging applications. This paper proposes the use of photorealistic synthetic imagery for training deep models that can be applied to interpret real-world underwater imagery. To demonstrate this concept, we look at the specific problem of biofouling detection on marine structures. A contemporary deep encoder–decoder network, termed SegNet, is trained using 2500 annotated synthetic images of size 960 × 540 pixels. The images were rendered in a virtual underwater environment under a wide variety of conditions and feature biofouling of various size, shape, and colour. Each rendered image has a corresponding ground truth per-pixel label map. Once trained on the synthetic imagery, SegNet is applied to segment new real-world images. The initial segmentation is refined using an iterative support vector machine (SVM) based post-processing algorithm. The proposed approach achieves a mean Intersection over Union (IoU) of 87% and a mean accuracy of 94% when tested on 32 frames extracted from two distinct real-world subsea inspection videos. Inference takes several seconds for a typical image." @default.
- W2886075188 created "2018-08-22" @default.
- W2886075188 creator A5031336210 @default.
- W2886075188 creator A5034110857 @default.
- W2886075188 creator A5072761721 @default.
- W2886075188 creator A5087383914 @default.
- W2886075188 date "2018-08-04" @default.
- W2886075188 modified "2023-10-17" @default.
- W2886075188 title "Semantic Segmentation of Underwater Imagery Using Deep Networks Trained on Synthetic Imagery" @default.
- W2886075188 cites W1563088657 @default.
- W2886075188 cites W1596173341 @default.
- W2886075188 cites W1903029394 @default.
- W2886075188 cites W1941370076 @default.
- W2886075188 cites W2037227137 @default.
- W2886075188 cites W2087347434 @default.
- W2886075188 cites W2097117768 @default.
- W2886075188 cites W2115579991 @default.
- W2886075188 cites W2125215748 @default.
- W2886075188 cites W2144794286 @default.
- W2886075188 cites W2171943915 @default.
- W2886075188 cites W2194775991 @default.
- W2886075188 cites W2431874326 @default.
- W2886075188 cites W2620240181 @default.
- W2886075188 cites W2625840998 @default.
- W2886075188 cites W2760200114 @default.
- W2886075188 cites W2765509090 @default.
- W2886075188 cites W2804860796 @default.
- W2886075188 cites W4239510810 @default.
- W2886075188 doi "https://doi.org/10.3390/jmse6030093" @default.
- W2886075188 hasPublicationYear "2018" @default.
- W2886075188 type Work @default.
- W2886075188 sameAs 2886075188 @default.
- W2886075188 citedByCount "43" @default.
- W2886075188 countsByYear W28860751882019 @default.
- W2886075188 countsByYear W28860751882020 @default.
- W2886075188 countsByYear W28860751882021 @default.
- W2886075188 countsByYear W28860751882022 @default.
- W2886075188 countsByYear W28860751882023 @default.
- W2886075188 crossrefType "journal-article" @default.
- W2886075188 hasAuthorship W2886075188A5031336210 @default.
- W2886075188 hasAuthorship W2886075188A5034110857 @default.
- W2886075188 hasAuthorship W2886075188A5072761721 @default.
- W2886075188 hasAuthorship W2886075188A5087383914 @default.
- W2886075188 hasBestOaLocation W28860751881 @default.
- W2886075188 hasConcept C108583219 @default.
- W2886075188 hasConcept C111368507 @default.
- W2886075188 hasConcept C12267149 @default.
- W2886075188 hasConcept C124504099 @default.
- W2886075188 hasConcept C127313418 @default.
- W2886075188 hasConcept C146849305 @default.
- W2886075188 hasConcept C153180895 @default.
- W2886075188 hasConcept C154945302 @default.
- W2886075188 hasConcept C160633673 @default.
- W2886075188 hasConcept C31972630 @default.
- W2886075188 hasConcept C41008148 @default.
- W2886075188 hasConcept C89600930 @default.
- W2886075188 hasConcept C98083399 @default.
- W2886075188 hasConceptScore W2886075188C108583219 @default.
- W2886075188 hasConceptScore W2886075188C111368507 @default.
- W2886075188 hasConceptScore W2886075188C12267149 @default.
- W2886075188 hasConceptScore W2886075188C124504099 @default.
- W2886075188 hasConceptScore W2886075188C127313418 @default.
- W2886075188 hasConceptScore W2886075188C146849305 @default.
- W2886075188 hasConceptScore W2886075188C153180895 @default.
- W2886075188 hasConceptScore W2886075188C154945302 @default.
- W2886075188 hasConceptScore W2886075188C160633673 @default.
- W2886075188 hasConceptScore W2886075188C31972630 @default.
- W2886075188 hasConceptScore W2886075188C41008148 @default.
- W2886075188 hasConceptScore W2886075188C89600930 @default.
- W2886075188 hasConceptScore W2886075188C98083399 @default.
- W2886075188 hasFunder F4320320847 @default.
- W2886075188 hasIssue "3" @default.
- W2886075188 hasLocation W28860751881 @default.
- W2886075188 hasLocation W28860751882 @default.
- W2886075188 hasOpenAccess W2886075188 @default.
- W2886075188 hasPrimaryLocation W28860751881 @default.
- W2886075188 hasRelatedWork W1999583034 @default.
- W2886075188 hasRelatedWork W2037375427 @default.
- W2886075188 hasRelatedWork W2773822314 @default.
- W2886075188 hasRelatedWork W2910761503 @default.
- W2886075188 hasRelatedWork W2953138830 @default.
- W2886075188 hasRelatedWork W3168963531 @default.
- W2886075188 hasRelatedWork W3176162126 @default.
- W2886075188 hasRelatedWork W3201231642 @default.
- W2886075188 hasRelatedWork W3217214504 @default.
- W2886075188 hasRelatedWork W4295532600 @default.
- W2886075188 hasVolume "6" @default.
- W2886075188 isParatext "false" @default.
- W2886075188 isRetracted "false" @default.
- W2886075188 magId "2886075188" @default.
- W2886075188 workType "article" @default.