3D reconstruction of a human body from multiple viewpoints

Authors:
Koichiro Yamauchi;Hideto Kameshima;Hideo Saito;Yukio Sato
Affiliations:
Graduate School of Science and Technology, Keio University, Yokohama, Japan;Graduate School of Science and Technology, Keio University, Yokohama, Japan;Graduate School of Science and Technology, Keio University, Yokohama, Japan;Graduate School of Science and Technology, Keio University, Yokohama, Japan
Venue:
PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology
Year:
2007

Citing 8
Cited 0

Accurate Rangefinder with Laser Pattern Shifting

ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
The space of human body shapes: reconstruction and parameterization from range scans

ACM SIGGRAPH 2003 Papers
Sizing us up

IEEE Spectrum
Protected interactive 3D graphics via remote rendering

ACM SIGGRAPH 2004 Papers
Image-based spatio-temporal modeling and view interpolation of dynamic events

ACM Transactions on Graphics (TOG)
Protecting 3d graphics content

Communications of the ACM - 3d hard copy
Learning a correlated model of identity and pose-dependent body shape variation for real-time synthesis

Proceedings of the 2006 ACM SIGGRAPH/Eurographics symposium on Computer animation
Appearance-based virtual view generation from multicamera videos captured in the 3-D room

IEEE Transactions on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

A human body measurement system using multiple viewpoints is proposed. Whole human body data taken from systems, which have been developed with a few viewpoints, have not been successful at acquiring due to occlusion. It is proposed that data can be successfully obtained by a method using multiple rangefinders correctly. Four compact rangefinders are installed in a pole. Those three pole units, with 12 rangefinders, are assigned around a person. Multiple viewpoint range images allow the 3D shape reconstruction of a human body. Then a morphable model is adapted to whole human body data. The measurement time is 2 seconds and the average error is found to be 1.88 mm. In this paper, the system configuration, calibration, morphable model and experimental results are described.