Translator Disclaimer
21 September 2015 Markerless motion capture based on diffusion geometry and silhouettes
Author Affiliations +
Markerless human motion capture has a wide variety of applications, but recovering a pose from multiple-view calibrated images remains challenging. In general, the problem of pose estimation is an optimization problem, but cost functions easily trapped in a local minimum based on extrinsic similarities (silhouette, edge, etc.) and pose estimation fail if the body is largely self-occluded. We define an effective cost function that combines extrinsic and intrinsic similarities, that can be translated by projecting a mesh model onto camera views to best match the silhouettes from an extrinsic point of view, and that attempts to preserve the intrinsic geometry of the shape using predefined mesh models based on heat diffusion. The results of experiment show that our proposed method is more robust for sequence motion capture than pure extrinsic similarity or pure intrinsic similarity.
© 2015 SPIE and IS&T 1017-9909/2015/$25.00 © 2015 SPIE and IS&T
Qinghua Liang and Zhenjiang Miao "Markerless motion capture based on diffusion geometry and silhouettes," Journal of Electronic Imaging 24(5), 051003 (21 September 2015).
Published: 21 September 2015


CIAO: Chandra's data analysis system
Proceedings of SPIE (June 30 2006)
Surface modeling in heart motion analysis
Proceedings of SPIE (February 01 1992)
Stereo-vision-based 3D modeling of space structures
Proceedings of SPIE (May 15 2007)
A visual tracking system using an RFID tag
Proceedings of SPIE (January 17 2005)

Back to Top