Optical Flow Estimation: An Error Analysis of Gradient-Based Methods with Local Optimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual reconstruction
Computation of component image velocity from local phase information
International Journal of Computer Vision
Computing optical flow across multiple scales: an adaptive coarse-to-fine strategy
International Journal of Computer Vision
Robust computation of optical flow in a multi-scale differential framework
International Journal of Computer Vision
The computation of optical flow
ACM Computing Surveys (CSUR)
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields
Computer Vision and Image Understanding
Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image Motion
International Journal of Computer Vision
Scale-Space Theory in Computer Vision
Scale-Space Theory in Computer Vision
Hierarchical Model-Based Motion Estimation
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Learned Models for Estimation of Rigid and ArticulatedHuman Motion from Stationary or Moving Camera
International Journal of Computer Vision
Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods
International Journal of Computer Vision
Hi-index | 0.00 |
A model for computing image flow in image sequencescontaining a very wide range of instantaneous flows is proposed. Thismodel integrates the spatio-temporal image derivatives from multipletemporal scales to provide both reliable and accurate instantaneousflow estimates. The integration employs robust regression andautomatic scale weighting in a generalized brightness constancyframework. In addition to instantaneous flow estimation the modelsupports recovery of dense estimates of image acceleration and can bereadily combined with parameterized flow and acceleration models. A demonstration of performance on image sequences of typical humanactions taken with a high frame-rate camera is given.