Direct estimation and error analysis for oriented patterns
CVGIP: Image Understanding
Dense Motion Analysis in Fluid Imagery
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Weighted and extended total variation for image restoration and decomposition
Pattern Recognition
A unified approach to shot change detection and camera motion characterization
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
Echo Particular Velocity Imaging (EchoPIV) has become a promising tool to detect flow patterns in cardiovascular structures. We present in this paper a new method for the detection and tracking of the vortex in the left ventricle for EchoPIV image sequences. The vortex is roughly localized by approximating an affine motion model to the estimated high density motion vector field and analyzing the significance of its rotational component in a statistical test. Based on a detection of the center of rotation and the approximated motion model, the area of the vortex is segmented. False positives are eliminated by analyzing the vortex's shape. Results on synthetic and real data are promising.