DocumentCode
2425354
Title
Building virtual human body from video
Author
Hoshnio, Junichi
Author_Institution
Coll. of Eng. Syst., Tsukuba Univ., Ibaraki, Japan
fYear
2002
fDate
2002
Firstpage
265
Lastpage
266
Abstract
We present a mode-based analysis and synthesis of human body images. First, we estimate the current 3D pose of a human figure by using the spatio-temporal analysis with kinematic constraints. Then, we store the intensity images of the human body as textures of the 3D body model. Such a human model can be used to generate multiple-views, merge virtual objects, and change motion characteristics of human figures in video
Keywords
image texture; solid modelling; user interfaces; virtual reality; 3D body model; 3D pose estimation; avatar; human body image synthesis; image textures; kinematic constraints; mode-based analysis; motion characteristics; spatio-temporal analysis; three dimensional body model; video; virtual human body; virtual object merging; virtual reality; Arm; Biological system modeling; Cameras; Character generation; Educational institutions; Humans; Leg; Merging; Motion estimation; Virtual reality;
fLanguage
English
Publisher
ieee
Conference_Titel
Virtual Reality, 2002. Proceedings. IEEE
Conference_Location
Orlando, FL
ISSN
1087-8270
Print_ISBN
0-7695-1492-8
Type
conf
DOI
10.1109/VR.2002.996530
Filename
996530
Link To Document