Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083543291> ?p ?o ?g. }
- W3083543291 endingPage "103383" @default.
- W3083543291 startingPage "103383" @default.
- W3083543291 abstract "At present, technologies based on deep learning methods for automated detection of sewer defects have been developing rapidly. In this study, a novel semantic segmentation network called PipeUNet is proposed for sewer defect segmentation. In order to enhance the feature extraction capability and resolve semantic differences between high level and low level features, a new module named feature reuse and attention mechanism block is added between the original skip connections of U-Net. Focal loss is adopted to solve the class imbalance problem. PipeUNet was trained using the CCTV images with typical defects including crack, infiltration, joint offset and intruding lateral. It was tested by the defects images and normal images to evaluate the network's defect segmentation and detection performance respectively. It achieved the highest Mean Intersection over Union of 76.37% which proved the proposed approach's efficiency. It can process CCTV images at a high speed of 32 images per second." @default.
- W3083543291 created "2020-09-11" @default.
- W3083543291 creator A5008695288 @default.
- W3083543291 creator A5044711844 @default.
- W3083543291 creator A5065308577 @default.
- W3083543291 creator A5084291326 @default.
- W3083543291 date "2020-11-01" @default.
- W3083543291 modified "2023-09-29" @default.
- W3083543291 title "Automatic sewer pipe defect semantic segmentation based on improved U-Net" @default.
- W3083543291 cites W1948860882 @default.
- W3083543291 cites W1963894246 @default.
- W3083543291 cites W1989587560 @default.
- W3083543291 cites W1994198993 @default.
- W3083543291 cites W2009434431 @default.
- W3083543291 cites W2013718062 @default.
- W3083543291 cites W2039183981 @default.
- W3083543291 cites W2049343907 @default.
- W3083543291 cites W2053889564 @default.
- W3083543291 cites W2057221234 @default.
- W3083543291 cites W2064985253 @default.
- W3083543291 cites W2065628349 @default.
- W3083543291 cites W2076365554 @default.
- W3083543291 cites W2076387959 @default.
- W3083543291 cites W2079629977 @default.
- W3083543291 cites W2097221445 @default.
- W3083543291 cites W2106238010 @default.
- W3083543291 cites W2412782625 @default.
- W3083543291 cites W2767106145 @default.
- W3083543291 cites W2792741217 @default.
- W3083543291 cites W2804860796 @default.
- W3083543291 cites W2889035772 @default.
- W3083543291 cites W2910124774 @default.
- W3083543291 cites W2913697492 @default.
- W3083543291 cites W2916429473 @default.
- W3083543291 cites W2963466857 @default.
- W3083543291 cites W2963881378 @default.
- W3083543291 cites W2982284503 @default.
- W3083543291 cites W2982512126 @default.
- W3083543291 doi "https://doi.org/10.1016/j.autcon.2020.103383" @default.
- W3083543291 hasPublicationYear "2020" @default.
- W3083543291 type Work @default.
- W3083543291 sameAs 3083543291 @default.
- W3083543291 citedByCount "42" @default.
- W3083543291 countsByYear W30835432912021 @default.
- W3083543291 countsByYear W30835432912022 @default.
- W3083543291 countsByYear W30835432912023 @default.
- W3083543291 crossrefType "journal-article" @default.
- W3083543291 hasAuthorship W3083543291A5008695288 @default.
- W3083543291 hasAuthorship W3083543291A5044711844 @default.
- W3083543291 hasAuthorship W3083543291A5065308577 @default.
- W3083543291 hasAuthorship W3083543291A5084291326 @default.
- W3083543291 hasConcept C111919701 @default.
- W3083543291 hasConcept C127413603 @default.
- W3083543291 hasConcept C138885662 @default.
- W3083543291 hasConcept C146978453 @default.
- W3083543291 hasConcept C153180895 @default.
- W3083543291 hasConcept C154945302 @default.
- W3083543291 hasConcept C175291020 @default.
- W3083543291 hasConcept C199360897 @default.
- W3083543291 hasConcept C206588197 @default.
- W3083543291 hasConcept C2776401178 @default.
- W3083543291 hasConcept C31972630 @default.
- W3083543291 hasConcept C41008148 @default.
- W3083543291 hasConcept C41895202 @default.
- W3083543291 hasConcept C52622490 @default.
- W3083543291 hasConcept C548081761 @default.
- W3083543291 hasConcept C64543145 @default.
- W3083543291 hasConcept C89600930 @default.
- W3083543291 hasConcept C98045186 @default.
- W3083543291 hasConceptScore W3083543291C111919701 @default.
- W3083543291 hasConceptScore W3083543291C127413603 @default.
- W3083543291 hasConceptScore W3083543291C138885662 @default.
- W3083543291 hasConceptScore W3083543291C146978453 @default.
- W3083543291 hasConceptScore W3083543291C153180895 @default.
- W3083543291 hasConceptScore W3083543291C154945302 @default.
- W3083543291 hasConceptScore W3083543291C175291020 @default.
- W3083543291 hasConceptScore W3083543291C199360897 @default.
- W3083543291 hasConceptScore W3083543291C206588197 @default.
- W3083543291 hasConceptScore W3083543291C2776401178 @default.
- W3083543291 hasConceptScore W3083543291C31972630 @default.
- W3083543291 hasConceptScore W3083543291C41008148 @default.
- W3083543291 hasConceptScore W3083543291C41895202 @default.
- W3083543291 hasConceptScore W3083543291C52622490 @default.
- W3083543291 hasConceptScore W3083543291C548081761 @default.
- W3083543291 hasConceptScore W3083543291C64543145 @default.
- W3083543291 hasConceptScore W3083543291C89600930 @default.
- W3083543291 hasConceptScore W3083543291C98045186 @default.
- W3083543291 hasFunder F4320334897 @default.
- W3083543291 hasLocation W30835432911 @default.
- W3083543291 hasOpenAccess W3083543291 @default.
- W3083543291 hasPrimaryLocation W30835432911 @default.
- W3083543291 hasRelatedWork W1669643531 @default.
- W3083543291 hasRelatedWork W2005437358 @default.
- W3083543291 hasRelatedWork W2008656436 @default.
- W3083543291 hasRelatedWork W2016461833 @default.
- W3083543291 hasRelatedWork W2039154422 @default.
- W3083543291 hasRelatedWork W2134924024 @default.
- W3083543291 hasRelatedWork W2382607599 @default.