Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804895> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4385804895 abstract "The paper discusses the need for a reliable and efficient computer vision system to inspect utility networks with minimal human involvement, due to the aging infrastructure of these networks. We propose a deep learning technique, Fusion-Semantic Utility Network (Fusion-SUNet), to classify the dense and irregular point clouds obtained from the airborne laser terrain mapping (ALTM) system used for data collection. The proposed network combines two networks to achieve voxel-based semantic segmentation of the point clouds at multi-resolution with object categories in three dimensions and predict two-dimensional regional labels distinguishing corridor regions from non-corridors. The network imposes spatial layout consistency on the features of the voxel-based 3D network using regional segmentation features. The authors demonstrate the effectiveness of the proposed technique by testing it on 67km <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> of utility corridor data with average density of 5pp/m <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> , achieving significantly better performance compared to the state-of-the-art baseline network, with an F1 score of 93% for pylon class, 99% for ground class, 99% for vegetation class, and 98% for powerline class." @default.
- W4385804895 created "2023-08-15" @default.
- W4385804895 creator A5036846355 @default.
- W4385804895 creator A5054546897 @default.
- W4385804895 creator A5067434544 @default.
- W4385804895 date "2023-06-01" @default.
- W4385804895 modified "2023-10-16" @default.
- W4385804895 title "Fusion-SUNet: Spatial Layout Consistency for 3D Semantic Segmentation" @default.
- W4385804895 cites W2098201806 @default.
- W4385804895 cites W2113325037 @default.
- W4385804895 cites W2125215748 @default.
- W4385804895 cites W2145769761 @default.
- W4385804895 cites W2334845011 @default.
- W4385804895 cites W2530023749 @default.
- W4385804895 cites W2739764235 @default.
- W4385804895 cites W2798637590 @default.
- W4385804895 cites W2899198239 @default.
- W4385804895 cites W2948290402 @default.
- W4385804895 cites W2963276418 @default.
- W4385804895 cites W2963640828 @default.
- W4385804895 cites W2963706542 @default.
- W4385804895 cites W2974535196 @default.
- W4385804895 cites W2982436005 @default.
- W4385804895 cites W2983441124 @default.
- W4385804895 cites W2990613095 @default.
- W4385804895 cites W3015550093 @default.
- W4385804895 cites W3091490581 @default.
- W4385804895 cites W3195533956 @default.
- W4385804895 cites W3207731722 @default.
- W4385804895 cites W4385711340 @default.
- W4385804895 doi "https://doi.org/10.1109/cvprw59228.2023.00698" @default.
- W4385804895 hasPublicationYear "2023" @default.
- W4385804895 type Work @default.
- W4385804895 citedByCount "0" @default.
- W4385804895 crossrefType "proceedings-article" @default.
- W4385804895 hasAuthorship W4385804895A5036846355 @default.
- W4385804895 hasAuthorship W4385804895A5054546897 @default.
- W4385804895 hasAuthorship W4385804895A5067434544 @default.
- W4385804895 hasConcept C124101348 @default.
- W4385804895 hasConcept C127413603 @default.
- W4385804895 hasConcept C131979681 @default.
- W4385804895 hasConcept C146978453 @default.
- W4385804895 hasConcept C153180895 @default.
- W4385804895 hasConcept C154945302 @default.
- W4385804895 hasConcept C19269812 @default.
- W4385804895 hasConcept C2776436953 @default.
- W4385804895 hasConcept C2777212361 @default.
- W4385804895 hasConcept C2781051052 @default.
- W4385804895 hasConcept C33954974 @default.
- W4385804895 hasConcept C41008148 @default.
- W4385804895 hasConcept C54170458 @default.
- W4385804895 hasConcept C89600930 @default.
- W4385804895 hasConceptScore W4385804895C124101348 @default.
- W4385804895 hasConceptScore W4385804895C127413603 @default.
- W4385804895 hasConceptScore W4385804895C131979681 @default.
- W4385804895 hasConceptScore W4385804895C146978453 @default.
- W4385804895 hasConceptScore W4385804895C153180895 @default.
- W4385804895 hasConceptScore W4385804895C154945302 @default.
- W4385804895 hasConceptScore W4385804895C19269812 @default.
- W4385804895 hasConceptScore W4385804895C2776436953 @default.
- W4385804895 hasConceptScore W4385804895C2777212361 @default.
- W4385804895 hasConceptScore W4385804895C2781051052 @default.
- W4385804895 hasConceptScore W4385804895C33954974 @default.
- W4385804895 hasConceptScore W4385804895C41008148 @default.
- W4385804895 hasConceptScore W4385804895C54170458 @default.
- W4385804895 hasConceptScore W4385804895C89600930 @default.
- W4385804895 hasFunder F4320334593 @default.
- W4385804895 hasLocation W43858048951 @default.
- W4385804895 hasOpenAccess W4385804895 @default.
- W4385804895 hasPrimaryLocation W43858048951 @default.
- W4385804895 hasRelatedWork W1990200345 @default.
- W4385804895 hasRelatedWork W2114282491 @default.
- W4385804895 hasRelatedWork W2984230369 @default.
- W4385804895 hasRelatedWork W3015465855 @default.
- W4385804895 hasRelatedWork W3028575330 @default.
- W4385804895 hasRelatedWork W3083637823 @default.
- W4385804895 hasRelatedWork W3107180823 @default.
- W4385804895 hasRelatedWork W4206076898 @default.
- W4385804895 hasRelatedWork W4214536195 @default.
- W4385804895 hasRelatedWork W4221144437 @default.
- W4385804895 isParatext "false" @default.
- W4385804895 isRetracted "false" @default.
- W4385804895 workType "article" @default.