Full metadata record
DC FieldValueLanguage
dc.contributor.authorPun, Iek-Kuongen_US
dc.contributor.authorLin, I-Chenen_US
dc.contributor.authorTang, Tsung-Hsienen_US
dc.date.accessioned2015-07-21T08:30:58Z-
dc.date.available2015-07-21T08:30:58Z-
dc.date.issued2013-01-01en_US
dc.identifier.isbn978-1-4799-2576-6en_US
dc.identifier.issnen_US
dc.identifier.urihttp://dx.doi.org/10.1109/CADGraphics.2013.34en_US
dc.identifier.urihttp://hdl.handle.net/11536/125168-
dc.description.abstractIn this paper, a markerless 3D hand tracking system for monocular RGB video is presented. We propose a novel two-level approach to efficiently grasp the personal characteristics and high varieties of hand postures. Our system first searches the approximate nearest neighbors in a small personalized real-hand image set, and retrieves more details from a large synthetic 3D hand posture database. Temporal consistency property is also utilized for disambiguating and noise reduction. Our prototype system can approximate hand poses including rigid and non-rigid out-of-image-plane rotation, slow and fast gesture changing during rotation. It can also recover from a short-term missing hand situation in an interactive rate.en_US
dc.language.isoen_USen_US
dc.subjecthand trackingen_US
dc.subject3D gestureen_US
dc.subjectadvanced interfaceen_US
dc.titleMarkerless 3D Hand Posture Estimation from Monocular Video by Two-level Searchingen_US
dc.typeProceedings Paperen_US
dc.identifier.doi10.1109/CADGraphics.2013.34en_US
dc.identifier.journal2013 INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN AND COMPUTER GRAPHICS (CAD/GRAPHICS)en_US
dc.citation.spage204en_US
dc.citation.epage211en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000355399900028en_US
dc.citation.woscount0en_US
Appears in Collections:Conferences Paper