Towards model-based capture of a persons shape, appearance and motion
- 1 September 1999
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper introduces a model-based approach to capturing a persons shape, appearance and movement. A 3D animated model of a clothed persons whole-body shape and appearance is automatically constructed from a set of orthogonal view color images. The reconstructed model of a person is then used together with the least-squares inverse-kinematics framework of Bregler et al. [4] to capture simple 3D movements from a video image sequence.Keywords
This publication has 12 references indexed in Scilit:
- Pfinder: real-time tracking of the human bodyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Tracking people with twists and exponential mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Automatic tracking of human motion in indoor scenes across multiple synchronized video streamsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Virtual people: capturing human models to populate virtual worldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Head Modeling from Pictures and Morphing in 3D with Image Metamorphosis Based on TriangulationPublished by Springer Nature ,1998
- Three-Dimensional Human Body Model Acquisition from Multiple ViewsInternational Journal of Computer Vision, 1998
- Tracking of persons in monocular image sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Virtual view generation for 3D digital videoIEEE MultiMedia, 1997
- 3D scanning in apparel design and human engineeringIEEE Computer Graphics and Applications, 1996
- Automatic creation of 3D facial modelsIEEE Computer Graphics and Applications, 1993