Human posture probability density estimation based on actual motion measurement and eigenpostures

2005 ◽  
Author(s):  
T. Harada ◽  
T. Mori ◽  
T. Sato
Keyword(s):  
Probability Density ◽  
Density Estimation ◽  
Probability Density Estimation ◽  
Motion Measurement ◽  
Human Posture ◽  
Actual Motion

scholarly journals Human Posture Probability Density Estimation Based on Actual Motion Measurement and Eigenpostures

2005 ◽  
Vol 17 (6) ◽  
pp. 664-671 ◽  
Author(s):  
Tatsuya Harada ◽  
◽  
Taketoshi Mori ◽  
Tomomasa Sato ◽  
Keyword(s):  
Euclidean Space ◽  
Probability Density ◽  
Human Motion ◽  
Density Estimator ◽  
Probability Density Estimation ◽  
Mechanical Motion ◽  
Motion Measurement ◽  
Human Posture ◽  
Unit Quaternions ◽  
Logarithmic Mapping

We construct human posture probability density based on actual human motion measurement. Human postures in daily life were measured for two days by having subjects wear a mechanical motion capture device. Accumulated human postures were converted to unit quaternions to guarantee the uniqueness of posture representation. To represent probability density effectively, we propose eigenpostures for posture compression and use the kernel-based reduced set density estimator (RSDE) to reduce the number of posture samples and construction of posture probability density. Before compression, unit quaternions were converted to Euclidean space by logarithmic mapping. After conversion, postures were compressed in Euclidean space. Applying constructed human posture probability density for unlikely posture detection and motion segmentation, we verified its effectiveness for many different applications.

Sign in / Sign up

Export Citation Format

Share Document