High quality depth maps generation of humans in monocular videos단안 영상에서의 인간 오브젝트에 대한 고품질 깊이정보 생성

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 874
  • Download : 0
We proposes an ecient method to match a human template model to a corresponding human object in a monocular video to estimate visually pleasing depths of the human at every frame. Instead of trying to match the silhouettes between the projection of a 3D template of a human and the corresponding 2D object, we propagate the partially retrieved depth toward the boundary of the object. Our system matches a given 3D template model to a person in a monocular video with a small number of user inputs. We render depth maps from the matched results. We overlay the depth maps and corresponding scenes in the video. The human object is divided into several regions based on the color information. Depth pixels corresponding to each segment are seprately propagated to ensure the detail of the results. We compared the result and depth maps painted by experienced artists. The comparison shows our method produces viable depth maps of humans in monocular videos effciently.
Advisors
Noh, Jun-Yongresearcher노준용
Description
한국과학기술원 : 문화기술대학원,
Publisher
한국과학기술원
Issue Date
2012
Identifier
509201/325007  / 020104330
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 문화기술대학원, 2012.8, [ iv, 20 p. ]

Keywords

Depth map; Image Processing; 깊이 정보; 이미지 처리; 포즈 최적화; Pose Estimation

URI
http://hdl.handle.net/10203/181119
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=509201&flag=dissertation
Appears in Collection
GCT-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0