Full metadata record
DC FieldValueLanguage
dc.contributor.authorChen, Zenen_US
dc.contributor.authorChen, Wen-Chaoen_US
dc.contributor.authorSung, Ping-Yien_US
dc.date.accessioned2014-12-08T15:35:41Z-
dc.date.available2014-12-08T15:35:41Z-
dc.date.issued2013en_US
dc.identifier.issn2330-7927en_US
dc.identifier.urihttp://hdl.handle.net/11536/24092-
dc.description.abstractThis paper presents a planar patch based method for 3D dense reconstruction. The object surface is represented as a point cloud. For high reconstruction accuracy and completeness, our strategy is to fit the object surface by planar patches at different scales. Furthermore, we apply adaptive weights to defme the photo-consistency measures for view matching. To optimize the view matching, we adopt a derivative-free GLN-PSO stochastic optimization method. Finally, to improve the reconstruction quality we design a patch priority queue for ordering the seed patches for patch expansion. The experimental results indicate the current implementation results are generally superior or comparable in comparison with the top ranked reconstruction methods reported in the Middlebury MVS website.en_US
dc.language.isoen_USen_US
dc.subjectPoint Clouden_US
dc.subjectAdaptive weighting Matching Measureen_US
dc.subjectGLN-PSOen_US
dc.subjectPatch Priority Queueen_US
dc.subjectPatch Expansion and Filteringen_US
dc.titleA NOVEL 3D DENSE RECONSTRUCTION WITH HIGH ACCURACY AND COMPLETENESSen_US
dc.typeProceedings Paperen_US
dc.identifier.journalELECTRONIC PROCEEDINGS OF THE 2013 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO WORKSHOPS (ICMEW)en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000335245800078-
Appears in Collections:Conferences Paper