Publication: 3D articulated shape segmentation using motion information
dc.contributor.department | Department of Computer Engineering | |
dc.contributor.department | N/A | |
dc.contributor.kuauthor | Yemez, Yücel | |
dc.contributor.kuauthor | Kalafatlar, Emre | |
dc.contributor.kuprofile | Faculty Member | |
dc.contributor.kuprofile | Master Student | |
dc.contributor.other | Department of Computer Engineering | |
dc.contributor.schoolcollegeinstitute | College of Engineering | |
dc.contributor.schoolcollegeinstitute | Graduate School of Sciences and Engineering | |
dc.contributor.yokid | 107907 | |
dc.contributor.yokid | N/A | |
dc.date.accessioned | 2024-11-09T23:06:43Z | |
dc.date.issued | 2010 | |
dc.description.abstract | We present a method for segmentation of articulated 3D shapes by incorporating the motion information obtained from time-varying models. We assume that the articulated shape is given in the form of a mesh sequence with fixed connectivity so that the inter-frame vertex correspondences, hence the vertex movements, are known a priori. We use different postures of an articulated shape in multiple frames to constitute an affinity matrix which encodes both temporal and spatial similarities between surface points. The shape is then decomposed into segments in spectral domain based on the affinity matrix using a standard K-means clustering algorithm. The performance of the proposed segmentation method is demonstrated on the mesh sequence of a human actor. | |
dc.description.indexedby | Scopus | |
dc.description.openaccess | YES | |
dc.description.publisherscope | International | |
dc.description.sponsoredbyTubitakEu | TÜBİTAK | |
dc.identifier.doi | 10.1109/ICPR.2010.877 | |
dc.identifier.isbn | 9780-7695-4109-9 | |
dc.identifier.issn | 1051-4651 | |
dc.identifier.link | https://www.scopus.com/inward/record.uri?eid=2-s2.0-78149480040anddoi=10.1109%2fICPR.2010.877andpartnerID=40andmd5=9d1cfedaa4408bb28aad3871ef13e7cb | |
dc.identifier.quartile | N/A | |
dc.identifier.scopus | 2-s2.0-78149480040 | |
dc.identifier.uri | http://dx.doi.org/10.1109/ICPR.2010.877 | |
dc.identifier.uri | https://hdl.handle.net/20.500.14288/9023 | |
dc.keywords | 3-D shape | |
dc.keywords | Affinity matrix | |
dc.keywords | Human actor | |
dc.keywords | Inter-frame | |
dc.keywords | K-Means clustering algorithm | |
dc.keywords | Motion information | |
dc.keywords | Multiple-frame | |
dc.keywords | Segmentation methods | |
dc.keywords | Shape segmentation | |
dc.keywords | Spatial similarity | |
dc.keywords | Spectral domains | |
dc.keywords | Surface points | |
dc.keywords | Time-varying models | |
dc.keywords | Vertex correspondence | |
dc.keywords | Clustering algorithms | |
dc.keywords | Pattern recognition | |
dc.keywords | Three dimensional | |
dc.language | English | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | |
dc.source | Proceedings - International Conference on Pattern Recognition | |
dc.subject | Computer engineering | |
dc.title | 3D articulated shape segmentation using motion information | |
dc.type | Conference proceeding | |
dspace.entity.type | Publication | |
local.contributor.authorid | 0000-0002-7515-3138 | |
local.contributor.authorid | N/A | |
local.contributor.kuauthor | Yemez, Yücel | |
local.contributor.kuauthor | Kalafatlar, Emre | |
relation.isOrgUnitOfPublication | 89352e43-bf09-4ef4-82f6-6f9d0174ebae | |
relation.isOrgUnitOfPublication.latestForDiscovery | 89352e43-bf09-4ef4-82f6-6f9d0174ebae |