             
|
|
|
Computer Graphics Forum
Volume22, Issue 3 (September 2003)
Authors:
D. Pritchard
Imager Laboratory, The University of British Columbia, Vancouver, Canada
W. Heidrich
Imager Laboratory, The University of British Columbia, Vancouver, Canada
Summary:
Recent years have seen an increased interest in motion capture systems. Current systems, however, are limitedto only a few degrees of freedom, so that effectively only the motion of linked rigid bodies can be acquired. Wepresent a system for the capture of deformable surfaces, most notably moving cloth, including both geometry andparameterisation. We recover geometry using stereo correspondence, and use the Scale Invariant Feature Transform(SIFT) to identify an arbitrary pattern printed on the cloth, even in the presence of fast motion. We describea novel seed-and-grow approach to adapt the SIFT algorithm to deformable geometry. Finally, we interpolatefeature points to parameterise the complete geometry.
Categories and Subject Descriptors (according to ACM CCS): I.3.5 [Computer Graphics]: Physically based modelingI.4.8 [Image Processing and Computer Vision]: Scene analysis