Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949653802> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2949653802 abstract "Robots typically possess sensors of different modalities, such as colour cameras, inertial measurement units, and 3D laser scanners. Often, solving a particular problem becomes easier when more than one modality is used. However, while there are undeniable benefits to combine sensors of different modalities the process tends to be complicated. Segmenting scenes observed by the robot into a discrete set of classes is a central requirement for autonomy as understanding the scene is the first step to reason about future situations. Scene segmentation is commonly performed using either image data or 3D point cloud data. In computer vision many successful methods for scene segmentation are based on conditional random fields (CRF) where the maximum a posteriori (MAP) solution to the segmentation can be obtained by inference. In this paper we devise a new CRF inference method for scene segmentation that incorporates global constraints, enforcing the sets of nodes are assigned the same class label. To do this efficiently, the CRF is formulated as a relaxed quadratic program whose MAP solution is found using a gradient-based optimisation approach. The proposed method is evaluated on images and 3D point cloud data gathered in urban environments where image data provides the appearance features needed by the CRF, while the 3D point cloud data provides global spatial constraints over sets of nodes. Comparisons with belief propagation, conventional quadratic programming relaxation, and higher order potential CRF show the benefits of the proposed method." @default.
- W2949653802 created "2019-06-27" @default.
- W2949653802 creator A5033725695 @default.
- W2949653802 creator A5045305458 @default.
- W2949653802 creator A5062619542 @default.
- W2949653802 date "2017-01-07" @default.
- W2949653802 modified "2023-09-27" @default.
- W2949653802 title "Urban Scene Segmentation with Laser-Constrained CRFs" @default.
- W2949653802 cites W1577575150 @default.
- W2949653802 cites W1971618559 @default.
- W2949653802 cites W1993846506 @default.
- W2949653802 cites W1999478155 @default.
- W2949653802 cites W2028284985 @default.
- W2949653802 cites W2033979122 @default.
- W2949653802 cites W2113940248 @default.
- W2949653802 cites W2115579991 @default.
- W2949653802 cites W2116877738 @default.
- W2949653802 cites W2121947440 @default.
- W2949653802 cites W2133916729 @default.
- W2949653802 cites W2144414892 @default.
- W2949653802 cites W2150796457 @default.
- W2949653802 cites W2152864241 @default.
- W2949653802 cites W2155853094 @default.
- W2949653802 cites W2169551590 @default.
- W2949653802 cites W2540072873 @default.
- W2949653802 hasPublicationYear "2017" @default.
- W2949653802 type Work @default.
- W2949653802 sameAs 2949653802 @default.
- W2949653802 citedByCount "0" @default.
- W2949653802 crossrefType "posted-content" @default.
- W2949653802 hasAuthorship W2949653802A5033725695 @default.
- W2949653802 hasAuthorship W2949653802A5045305458 @default.
- W2949653802 hasAuthorship W2949653802A5062619542 @default.
- W2949653802 hasConcept C111472728 @default.
- W2949653802 hasConcept C124504099 @default.
- W2949653802 hasConcept C131979681 @default.
- W2949653802 hasConcept C138885662 @default.
- W2949653802 hasConcept C152565575 @default.
- W2949653802 hasConcept C154945302 @default.
- W2949653802 hasConcept C2775953691 @default.
- W2949653802 hasConcept C2776214188 @default.
- W2949653802 hasConcept C2778045648 @default.
- W2949653802 hasConcept C31972630 @default.
- W2949653802 hasConcept C41008148 @default.
- W2949653802 hasConcept C75553542 @default.
- W2949653802 hasConcept C89600930 @default.
- W2949653802 hasConceptScore W2949653802C111472728 @default.
- W2949653802 hasConceptScore W2949653802C124504099 @default.
- W2949653802 hasConceptScore W2949653802C131979681 @default.
- W2949653802 hasConceptScore W2949653802C138885662 @default.
- W2949653802 hasConceptScore W2949653802C152565575 @default.
- W2949653802 hasConceptScore W2949653802C154945302 @default.
- W2949653802 hasConceptScore W2949653802C2775953691 @default.
- W2949653802 hasConceptScore W2949653802C2776214188 @default.
- W2949653802 hasConceptScore W2949653802C2778045648 @default.
- W2949653802 hasConceptScore W2949653802C31972630 @default.
- W2949653802 hasConceptScore W2949653802C41008148 @default.
- W2949653802 hasConceptScore W2949653802C75553542 @default.
- W2949653802 hasConceptScore W2949653802C89600930 @default.
- W2949653802 hasLocation W29496538021 @default.
- W2949653802 hasOpenAccess W2949653802 @default.
- W2949653802 hasPrimaryLocation W29496538021 @default.
- W2949653802 hasRelatedWork W127764718 @default.
- W2949653802 hasRelatedWork W1556691776 @default.
- W2949653802 hasRelatedWork W196305894 @default.
- W2949653802 hasRelatedWork W2100529712 @default.
- W2949653802 hasRelatedWork W2468423593 @default.
- W2949653802 hasRelatedWork W2523106987 @default.
- W2949653802 hasRelatedWork W2562018217 @default.
- W2949653802 hasRelatedWork W2781182312 @default.
- W2949653802 hasRelatedWork W2786350692 @default.
- W2949653802 hasRelatedWork W2795295712 @default.
- W2949653802 hasRelatedWork W2804176584 @default.
- W2949653802 hasRelatedWork W2907846557 @default.
- W2949653802 hasRelatedWork W2990109777 @default.
- W2949653802 hasRelatedWork W2991779855 @default.
- W2949653802 hasRelatedWork W3110765128 @default.
- W2949653802 hasRelatedWork W3127986322 @default.
- W2949653802 hasRelatedWork W3134051502 @default.
- W2949653802 hasRelatedWork W3190099185 @default.
- W2949653802 hasRelatedWork W5999557 @default.
- W2949653802 hasRelatedWork W2612941277 @default.
- W2949653802 isParatext "false" @default.
- W2949653802 isRetracted "false" @default.
- W2949653802 magId "2949653802" @default.
- W2949653802 workType "article" @default.