Gramians, generalized inverses, and the least squares approximation of optical flow.
Roger W. BrockettPublished in: ICRA (1987)
Keyphrases
- least squares
- optical flow
- image sequences
- motion parameters
- matrix approximation
- policy evaluation
- optical flow computation
- computer vision
- motion model
- parameter estimation
- optical flow estimation
- closed form
- error bounds
- motion field
- convex functions
- motion segmentation
- camera motion
- feature tracking
- levenberg marquardt
- flow field
- approximation algorithms
- sufficient conditions
- motion estimation
- robust estimation
- d scene
- curve fitting
- qualitative and quantitative evaluation
- approximation methods
- moving objects
- three dimensional
- sparse linear
- smooth functions
- set of basis functions
- neural network