Experience with 3D Optical Flow on Gated MRI Cardiac Datasets
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Performance characterization in computer vision: A guide to best practices
Computer Vision and Image Understanding
Hi-index | 0.00 |
3D Doppler Radar is a key forecasting tool for severe weather storms and automatic tracking of these deformable objects is of great interest to meteorologists, Currently, we use the notion of a 3D ellipsoid to represent the uncertainty of a storm's 3D center in the Doppler precipitation data and have described elsewhere an algebra for its use in storm tracking. In this paper, we describe how we use 3D velocity data computed by an iterative 3D least squares/regularization algorithm to construct a velocity compatibility function that uses a prediction/verification calculation to rate the "goodness" of potential storm matches. We also use the hypothesis that the orientation of matched storms should change smoothly to obtain improved matching.