Matches in SemOpenAlex for { <https://semopenalex.org/work/W2135249503> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2135249503 abstract "Unsupervised over-segmentation of an image into regions of perceptually similar pixels, known as super pixels, is a widely used preprocessing step in segmentation algorithms. Super pixel methods reduce the number of regions that must be considered later by more computationally expensive algorithms, with a minimal loss of information. Nevertheless, as some information is inevitably lost, it is vital that super pixels not cross object boundaries, as such errors will propagate through later steps. Existing methods make use of projected color or depth information, but do not consider three dimensional geometric relationships between observed data points which can be used to prevent super pixels from crossing regions of empty space. We propose a novel over-segmentation algorithm which uses voxel relationships to produce over-segmentations which are fully consistent with the spatial geometry of the scene in three dimensional, rather than projective, space. Enforcing the constraint that segmented regions must have spatial connectivity prevents label flow across semantic object boundaries which might otherwise be violated. Additionally, as the algorithm works directly in 3D space, observations from several calibrated RGB+D cameras can be segmented jointly. Experiments on a large data set of human annotated RGB+D images demonstrate a significant reduction in occurrence of clusters crossing object boundaries, while maintaining speeds comparable to state-of-the-art 2D methods." @default.
- W2135249503 created "2016-06-24" @default.
- W2135249503 creator A5006220439 @default.
- W2135249503 creator A5023811677 @default.
- W2135249503 creator A5033985832 @default.
- W2135249503 creator A5034989786 @default.
- W2135249503 date "2013-06-01" @default.
- W2135249503 modified "2023-10-10" @default.
- W2135249503 title "Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds" @default.
- W2135249503 cites W1515999713 @default.
- W2135249503 cites W1548953334 @default.
- W2135249503 cites W1601176293 @default.
- W2135249503 cites W2061202859 @default.
- W2135249503 cites W2096521559 @default.
- W2135249503 cites W2104125540 @default.
- W2135249503 cites W2118246710 @default.
- W2135249503 cites W2119531662 @default.
- W2135249503 cites W2156222070 @default.
- W2135249503 cites W2160821342 @default.
- W2135249503 cites W2293105860 @default.
- W2135249503 cites W2545985378 @default.
- W2135249503 doi "https://doi.org/10.1109/cvpr.2013.264" @default.
- W2135249503 hasPublicationYear "2013" @default.
- W2135249503 type Work @default.
- W2135249503 sameAs 2135249503 @default.
- W2135249503 citedByCount "332" @default.
- W2135249503 countsByYear W21352495032013 @default.
- W2135249503 countsByYear W21352495032014 @default.
- W2135249503 countsByYear W21352495032015 @default.
- W2135249503 countsByYear W21352495032016 @default.
- W2135249503 countsByYear W21352495032017 @default.
- W2135249503 countsByYear W21352495032018 @default.
- W2135249503 countsByYear W21352495032019 @default.
- W2135249503 countsByYear W21352495032020 @default.
- W2135249503 countsByYear W21352495032021 @default.
- W2135249503 countsByYear W21352495032022 @default.
- W2135249503 countsByYear W21352495032023 @default.
- W2135249503 crossrefType "proceedings-article" @default.
- W2135249503 hasAuthorship W2135249503A5006220439 @default.
- W2135249503 hasAuthorship W2135249503A5023811677 @default.
- W2135249503 hasAuthorship W2135249503A5033985832 @default.
- W2135249503 hasAuthorship W2135249503A5034989786 @default.
- W2135249503 hasBestOaLocation W21352495032 @default.
- W2135249503 hasConcept C124504099 @default.
- W2135249503 hasConcept C131979681 @default.
- W2135249503 hasConcept C153180895 @default.
- W2135249503 hasConcept C154945302 @default.
- W2135249503 hasConcept C160633673 @default.
- W2135249503 hasConcept C2781238097 @default.
- W2135249503 hasConcept C31972630 @default.
- W2135249503 hasConcept C34736171 @default.
- W2135249503 hasConcept C41008148 @default.
- W2135249503 hasConcept C54170458 @default.
- W2135249503 hasConcept C82990744 @default.
- W2135249503 hasConcept C89600930 @default.
- W2135249503 hasConceptScore W2135249503C124504099 @default.
- W2135249503 hasConceptScore W2135249503C131979681 @default.
- W2135249503 hasConceptScore W2135249503C153180895 @default.
- W2135249503 hasConceptScore W2135249503C154945302 @default.
- W2135249503 hasConceptScore W2135249503C160633673 @default.
- W2135249503 hasConceptScore W2135249503C2781238097 @default.
- W2135249503 hasConceptScore W2135249503C31972630 @default.
- W2135249503 hasConceptScore W2135249503C34736171 @default.
- W2135249503 hasConceptScore W2135249503C41008148 @default.
- W2135249503 hasConceptScore W2135249503C54170458 @default.
- W2135249503 hasConceptScore W2135249503C82990744 @default.
- W2135249503 hasConceptScore W2135249503C89600930 @default.
- W2135249503 hasLocation W21352495031 @default.
- W2135249503 hasLocation W21352495032 @default.
- W2135249503 hasOpenAccess W2135249503 @default.
- W2135249503 hasPrimaryLocation W21352495031 @default.
- W2135249503 hasRelatedWork W1998563493 @default.
- W2135249503 hasRelatedWork W2016533837 @default.
- W2135249503 hasRelatedWork W2741749319 @default.
- W2135249503 hasRelatedWork W2892386716 @default.
- W2135249503 hasRelatedWork W3027020613 @default.
- W2135249503 hasRelatedWork W3137866197 @default.
- W2135249503 hasRelatedWork W3167885074 @default.
- W2135249503 hasRelatedWork W4306164210 @default.
- W2135249503 hasRelatedWork W4313316311 @default.
- W2135249503 hasRelatedWork W4362608745 @default.
- W2135249503 isParatext "false" @default.
- W2135249503 isRetracted "false" @default.
- W2135249503 magId "2135249503" @default.
- W2135249503 workType "article" @default.