Periodic Nonlinear Principal Component Neural Networks for Humanoid Motion Segmentation, Generalization, and Generation.
Karl F. MacDormanRawichote ChalodhornMinoru AsadaPublished in: ICPR (4) (2004)
Keyphrases
- motion segmentation
- principal components
- neural network
- principal curves
- image sequences
- principal component analysis
- moving objects
- motion estimation
- model selection
- multibody
- motion model
- missing data
- epipolar geometry estimation
- dynamic scenes
- principal component regression
- pattern recognition
- dimensionality reduction
- optical flow
- flow field
- humanoid robot
- spectral clustering
- motion field
- kernel space
- multiple moving objects
- human motion
- feature tracking
- machine learning
- similarity measure
- low dimensional
- motion capture
- face recognition
- three dimensional
- computer vision