完整後設資料紀錄
DC 欄位語言
dc.contributor.authorCheng, Hsin-Minen_US
dc.contributor.authorTseng, Chen-Yuen_US
dc.contributor.authorHsin, Cheng-Hoen_US
dc.contributor.authorWang, Sheng-Jyhen_US
dc.date.accessioned2015-07-21T08:31:02Z-
dc.date.available2015-07-21T08:31:02Z-
dc.date.issued2013-01-01en_US
dc.identifier.isbn978-1-4799-2341-0en_US
dc.identifier.issn1522-4880en_US
dc.identifier.urihttp://hdl.handle.net/11536/125061-
dc.description.abstractIn this paper, we focus on recovering a 3-D depth map from a single image. Given an image of urban scene, we extract linear perspective information to establish the 3-D scene model. Unlike approaches which use only occlusion relationship between objects to estimate the relative depth of the image, we further combine the perspective geometry information with the occlusion relationship between objects. Besides, we propose the construction of depth gradient maps to represent the depth variation trend along the vertical and horizontal directions. The image is first partitioned into geometric components and initial depth gradient maps are generated based on the relative position between the vanishing point and the classified components. Incorporating main directions of vanishing lines and occlusion boundaries in the initial depth gradient maps, a refined depth map is obtained by using a CRF (conditional random field) model. We demonstrate that our approach can produce realistic relative depth maps for images of urban scenes.en_US
dc.language.isoen_USen_US
dc.subjectDepth estimationen_US
dc.subject3-D depth recoveryen_US
dc.titleSINGLE-IMAGE 3-D DEPTH ESTIMATION FOR URBAN SCENESen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013)en_US
dc.citation.spage2121en_US
dc.citation.epage2125en_US
dc.contributor.department電子工程學系及電子研究所zh_TW
dc.contributor.departmentDepartment of Electronics Engineering and Institute of Electronicsen_US
dc.identifier.wosnumberWOS:000351597602046en_US
dc.citation.woscount0en_US
顯示於類別:會議論文