Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947667882> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2947667882 endingPage "68" @default.
- W2947667882 startingPage "61" @default.
- W2947667882 abstract "Abstract. Industrial companies often require complete inventories of their infrastructure. In many cases, a better inventory leads to a direct reduction of cost and uncertainty of engineering. While large scale panoramic surveys now allow these inventories to be performed remotely and reduce time on-site, the time and money required to visually segment the many types of components on thousands of high resolution panoramas can make the process infeasible. Recent studies have shown that deep learning techniques, namely deep neural networks, can accurately perform panoptic segmentation of things and stuff and hence be used to inventory the components of a picture. In order to train those deep architectures with specific industrial equipment, not available in public datasets, our approach uses an as-built 3D model of an industrial building to procedurally generate labels. Our results show that, despite the presence of errors during the generation of the dataset, our method is able to accurately perform panoptic segmentation on images of industrial scenes. In our testing, 80% of generated labels were correctly identified (non null intersection over union, i.e. true positive) by the panoptic segmentation, with great performance levels even for difficult classes, such as reflective heat insulators. We then visually investigated the 20% of true negative, and discovered that 80% were correctly segmented, but were counted as true negative because of errors in the dataset generation. Demonstrating this level of accuracy for panoptic segmentation on industrial panoramas for inventories also offers novel perspectives for 3D laser scan processing." @default.
- W2947667882 created "2019-06-07" @default.
- W2947667882 creator A5053521247 @default.
- W2947667882 creator A5062575053 @default.
- W2947667882 creator A5089529308 @default.
- W2947667882 date "2019-05-29" @default.
- W2947667882 modified "2023-10-01" @default.
- W2947667882 title "USING 3D MODELS TO GENERATE LABELS FOR PANOPTIC SEGMENTATION OF INDUSTRIAL SCENES" @default.
- W2947667882 cites W1585910451 @default.
- W2947667882 cites W2185101813 @default.
- W2947667882 cites W2194775991 @default.
- W2947667882 cites W2341569833 @default.
- W2947667882 cites W2413409057 @default.
- W2947667882 cites W2561196672 @default.
- W2947667882 cites W2798040152 @default.
- W2947667882 cites W2804860796 @default.
- W2947667882 cites W2890715498 @default.
- W2947667882 cites W2952865063 @default.
- W2947667882 cites W2962759496 @default.
- W2947667882 cites W2963446712 @default.
- W2947667882 cites W2964062501 @default.
- W2947667882 doi "https://doi.org/10.5194/isprs-annals-iv-2-w5-61-2019" @default.
- W2947667882 hasPublicationYear "2019" @default.
- W2947667882 type Work @default.
- W2947667882 sameAs 2947667882 @default.
- W2947667882 citedByCount "3" @default.
- W2947667882 countsByYear W29476678822021 @default.
- W2947667882 countsByYear W29476678822023 @default.
- W2947667882 crossrefType "journal-article" @default.
- W2947667882 hasAuthorship W2947667882A5053521247 @default.
- W2947667882 hasAuthorship W2947667882A5062575053 @default.
- W2947667882 hasAuthorship W2947667882A5089529308 @default.
- W2947667882 hasBestOaLocation W29476678821 @default.
- W2947667882 hasConcept C108583219 @default.
- W2947667882 hasConcept C111919701 @default.
- W2947667882 hasConcept C138569888 @default.
- W2947667882 hasConcept C153180895 @default.
- W2947667882 hasConcept C154945302 @default.
- W2947667882 hasConcept C17744445 @default.
- W2947667882 hasConcept C199539241 @default.
- W2947667882 hasConcept C205649164 @default.
- W2947667882 hasConcept C2778755073 @default.
- W2947667882 hasConcept C31972630 @default.
- W2947667882 hasConcept C41008148 @default.
- W2947667882 hasConcept C58640448 @default.
- W2947667882 hasConcept C89600930 @default.
- W2947667882 hasConcept C94625758 @default.
- W2947667882 hasConcept C98045186 @default.
- W2947667882 hasConceptScore W2947667882C108583219 @default.
- W2947667882 hasConceptScore W2947667882C111919701 @default.
- W2947667882 hasConceptScore W2947667882C138569888 @default.
- W2947667882 hasConceptScore W2947667882C153180895 @default.
- W2947667882 hasConceptScore W2947667882C154945302 @default.
- W2947667882 hasConceptScore W2947667882C17744445 @default.
- W2947667882 hasConceptScore W2947667882C199539241 @default.
- W2947667882 hasConceptScore W2947667882C205649164 @default.
- W2947667882 hasConceptScore W2947667882C2778755073 @default.
- W2947667882 hasConceptScore W2947667882C31972630 @default.
- W2947667882 hasConceptScore W2947667882C41008148 @default.
- W2947667882 hasConceptScore W2947667882C58640448 @default.
- W2947667882 hasConceptScore W2947667882C89600930 @default.
- W2947667882 hasConceptScore W2947667882C94625758 @default.
- W2947667882 hasConceptScore W2947667882C98045186 @default.
- W2947667882 hasLocation W29476678821 @default.
- W2947667882 hasLocation W29476678822 @default.
- W2947667882 hasOpenAccess W2947667882 @default.
- W2947667882 hasPrimaryLocation W29476678821 @default.
- W2947667882 hasRelatedWork W1669643531 @default.
- W2947667882 hasRelatedWork W1982826852 @default.
- W2947667882 hasRelatedWork W2005437358 @default.
- W2947667882 hasRelatedWork W2008656436 @default.
- W2947667882 hasRelatedWork W2023558673 @default.
- W2947667882 hasRelatedWork W2110230079 @default.
- W2947667882 hasRelatedWork W2134924024 @default.
- W2947667882 hasRelatedWork W2517104666 @default.
- W2947667882 hasRelatedWork W2613186388 @default.
- W2947667882 hasRelatedWork W2790662084 @default.
- W2947667882 hasVolume "IV-2/W5" @default.
- W2947667882 isParatext "false" @default.
- W2947667882 isRetracted "false" @default.
- W2947667882 magId "2947667882" @default.
- W2947667882 workType "article" @default.