Realistic synthesis of novel human movements from a database of motion capture examples
- 1 December 2000
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 137-142
- https://doi.org/10.1109/humo.2000.897383
Abstract
Presents a system that can synthesize novel motion sequences from a database of motion capture examples. This is achieved through learning a statistical model from the captured data which enables the realistic synthesis of new movements by sampling the original captured sequences. New movements are synthesized by specifying the start and end keyframes. The statistical model identifies segments of the original motion capture data to generate novel motion sequences between the keyframes. The advantage of this approach is that it combines the flexibility of keyframe animation with the realism of motion capture data.Keywords
This publication has 8 references indexed in Scilit:
- Learning structured behaviour models using variable length Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The acquisition and use of interaction behaviour modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Animating by multi-level samplingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Human Motion Analysis: A ReviewComputer Vision and Image Understanding, 1999
- Shadow puppetryPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- A Framework for Uncertainty and Validation of 3-D Registration Methods Based on Points and FramesInternational Journal of Computer Vision, 1997
- Euler Angle ConversionPublished by Elsevier ,1994
- Vector quantization in speech codingProceedings of the IEEE, 1985