Matches in SemOpenAlex for { <https://semopenalex.org/work/W1988545226> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W1988545226 abstract "Segmentation of a scene to the part made is a challenging work. In this paper a graphical model is used for this task. The methods based on geometrical derivatives such as curvature and normal often haven't good result in segmentation of geometrically-complex architecture and lead to over-segmentation and even failure. Proposed method for segmentation contains two steps. At first region growing based on curvature, normal and color is used for growing region. This segmented cloud is used for unary potential in graphical model. Fully connected graph for Conditional Random Field with Gaussian kernel for pair wise potentials is used for correcting this segmentation. Gaussian kernels are based on appearance, smoothness and surface. This leads to high computational complexity since the model is fully connected and in every step of message passing needs to compute this Gaussian kernel between each node with all of the others node. Efficient Inference with Permutohedral high dimensional Lattice is used for doing this computation with high speed. This method is tested on challenging NYU depth 1 dataset with complicated geometry and results shows that the scene can segment to the part made it with high accuracy." @default.
- W1988545226 created "2016-06-24" @default.
- W1988545226 creator A5012933659 @default.
- W1988545226 creator A5037904553 @default.
- W1988545226 creator A5086365282 @default.
- W1988545226 date "2014-05-01" @default.
- W1988545226 modified "2023-09-26" @default.
- W1988545226 title "RGB-D scene segmentation with Conditional Random Field" @default.
- W1988545226 cites W1637459849 @default.
- W1988545226 cites W1964772475 @default.
- W1988545226 cites W1982387979 @default.
- W1988545226 cites W1996688648 @default.
- W1988545226 cites W2074658631 @default.
- W1988545226 cites W2075690349 @default.
- W1988545226 cites W2085411191 @default.
- W1988545226 cites W2125298120 @default.
- W1988545226 cites W2143939524 @default.
- W1988545226 cites W2562444477 @default.
- W1988545226 cites W27675589 @default.
- W1988545226 cites W2952793010 @default.
- W1988545226 doi "https://doi.org/10.1109/ikt.2014.7030347" @default.
- W1988545226 hasPublicationYear "2014" @default.
- W1988545226 type Work @default.
- W1988545226 sameAs 1988545226 @default.
- W1988545226 citedByCount "0" @default.
- W1988545226 crossrefType "proceedings-article" @default.
- W1988545226 hasAuthorship W1988545226A5012933659 @default.
- W1988545226 hasAuthorship W1988545226A5037904553 @default.
- W1988545226 hasAuthorship W1988545226A5086365282 @default.
- W1988545226 hasConcept C11413529 @default.
- W1988545226 hasConcept C121332964 @default.
- W1988545226 hasConcept C124504099 @default.
- W1988545226 hasConcept C131979681 @default.
- W1988545226 hasConcept C152565575 @default.
- W1988545226 hasConcept C154945302 @default.
- W1988545226 hasConcept C155846161 @default.
- W1988545226 hasConcept C163716315 @default.
- W1988545226 hasConcept C195065555 @default.
- W1988545226 hasConcept C2524010 @default.
- W1988545226 hasConcept C31972630 @default.
- W1988545226 hasConcept C33923547 @default.
- W1988545226 hasConcept C41008148 @default.
- W1988545226 hasConcept C5134670 @default.
- W1988545226 hasConcept C62520636 @default.
- W1988545226 hasConcept C65885262 @default.
- W1988545226 hasConcept C89600930 @default.
- W1988545226 hasConceptScore W1988545226C11413529 @default.
- W1988545226 hasConceptScore W1988545226C121332964 @default.
- W1988545226 hasConceptScore W1988545226C124504099 @default.
- W1988545226 hasConceptScore W1988545226C131979681 @default.
- W1988545226 hasConceptScore W1988545226C152565575 @default.
- W1988545226 hasConceptScore W1988545226C154945302 @default.
- W1988545226 hasConceptScore W1988545226C155846161 @default.
- W1988545226 hasConceptScore W1988545226C163716315 @default.
- W1988545226 hasConceptScore W1988545226C195065555 @default.
- W1988545226 hasConceptScore W1988545226C2524010 @default.
- W1988545226 hasConceptScore W1988545226C31972630 @default.
- W1988545226 hasConceptScore W1988545226C33923547 @default.
- W1988545226 hasConceptScore W1988545226C41008148 @default.
- W1988545226 hasConceptScore W1988545226C5134670 @default.
- W1988545226 hasConceptScore W1988545226C62520636 @default.
- W1988545226 hasConceptScore W1988545226C65885262 @default.
- W1988545226 hasConceptScore W1988545226C89600930 @default.
- W1988545226 hasLocation W19885452261 @default.
- W1988545226 hasOpenAccess W1988545226 @default.
- W1988545226 hasPrimaryLocation W19885452261 @default.
- W1988545226 hasRelatedWork W148539474 @default.
- W1988545226 hasRelatedWork W196213115 @default.
- W1988545226 hasRelatedWork W1964623265 @default.
- W1988545226 hasRelatedWork W2163096274 @default.
- W1988545226 hasRelatedWork W2403161956 @default.
- W1988545226 hasRelatedWork W2612440311 @default.
- W1988545226 hasRelatedWork W2620516784 @default.
- W1988545226 hasRelatedWork W2783083800 @default.
- W1988545226 hasRelatedWork W2888848076 @default.
- W1988545226 hasRelatedWork W2901835950 @default.
- W1988545226 hasRelatedWork W2936182668 @default.
- W1988545226 hasRelatedWork W2980531997 @default.
- W1988545226 hasRelatedWork W2995235358 @default.
- W1988545226 hasRelatedWork W3017056634 @default.
- W1988545226 hasRelatedWork W3048102697 @default.
- W1988545226 hasRelatedWork W3145550990 @default.
- W1988545226 hasRelatedWork W2098649500 @default.
- W1988545226 hasRelatedWork W2254183608 @default.
- W1988545226 hasRelatedWork W2959641995 @default.
- W1988545226 hasRelatedWork W2968138320 @default.
- W1988545226 isParatext "false" @default.
- W1988545226 isRetracted "false" @default.
- W1988545226 magId "1988545226" @default.
- W1988545226 workType "article" @default.