A periodic optical flow model for cardiac gated images

Authors:
Ling Li;Xiaofeng Niu;Yongyi Yang
Affiliations:
Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL;Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL;Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL
Venue:
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Year:
2009

Citing 6
Cited 0

An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences

IEEE Transactions on Pattern Analysis and Machine Intelligence
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields

Computer Vision and Image Understanding
A Theoretical Framework for Convex Regularizers in PDE-Based Computation of Image Motion

International Journal of Computer Vision
Extending the 'Oriented Smoothness Constraint' into the Temporal Domain and the Estimation of Derivatives of Optical Flow

ECCV '90 Proceedings of the First European Conference on Computer Vision
An iterative image registration technique with an application to stereo vision

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Tomographic Reconstruction of Dynamic Cardiac Image Sequences

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

For the purpose of motion-compensated processing we propose a temporal modeling approach for determining the image motion in a gated cardiac sequence, wherein the inherent image motion is periodic over time. To exploit the periodic nature of the cardiac motion, we use a Fourier harmonic representation to describe the motion field for the entire sequence. We then determine the motion field by estimating the parameters of this representation model. This joint estimation approach can take advantage of the statistics of all the available image data in the sequence. In the experiments, we applied the proposed approach to motion-compensated 4D reconstruction of gated cardiac SPECT images. Our results demonstrate that it could achieve robust estimation of the motion field and lead to improved image reconstruction despite the presence of strong imaging noise.