Show simple item record

dc.contributor.authorSpina, Sandroen_US
dc.contributor.authorDebattista, Kurten_US
dc.contributor.authorBugeja, Keithen_US
dc.contributor.authorChalmers, Alanen_US
dc.contributor.editorJohn Keyser and Young J. Kim and Peter Wonkaen_US
dc.date.accessioned2014-12-16T07:23:00Z
dc.date.available2014-12-16T07:23:00Z
dc.date.issued2014en_US
dc.identifier.isbn978-3-905674-73-6en_US
dc.identifier.urihttp://dx.doi.org/10.2312/pgs.20141244en_US
dc.description.abstractThe continuous development of new commodity hardware intended to capture the surface structure of objects is quickly making point cloud data ubiquitous. Scene understanding methods address the problem of determining the objects present in a point cloud which, dependant on sensor capabilities and object occlusions, is normally noisy and incomplete. In this paper, we propose a novel technique which enables automatic identification of semantically meaningful structures within point clouds acquired using different sensors on a variety of scenes. The representation model, namely the structure graph, with nodes representing planar surface segments, is computed over these point clouds to help with the identification task. In order to accommodate for more complex objects (e.g. chair, couch, cabinet, table), a training process is used to determine and concisely describe, within each object's structure graph, its important shape characteristics. Results on a variety of point clouds show how our method can quickly discern certain object types.en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectI.3.0 [Computer Graphics]en_US
dc.subjectGeneralen_US
dc.subjectI.3.5 [Computer Graphics]en_US
dc.subjectBoundary Representationen_US
dc.subjectI.3.8 [Computer Graphics]en_US
dc.subjectApplicationsen_US
dc.titleScene Segmentation and Understanding for Context-Free Point Cloudsen_US
dc.description.seriesinformationPacific Graphics Short Papersen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record