Optical Flow as a Tool for Cardiac Motion Estimation

Abstract

A sparse based algorithm for optical flow estimation is presented and compared with several classical optical flow estimation algorithms. The comparison is performed using several video sequences available from the Middlebury benchmark where the ground truth optical flow is known. The sparse algorithm attains competitive results with average angular errors as low as 2.09° and average magnitude errors as low as 0.100. The algorithms are also tested using a 4-D cardiac Magnetic Resonance Image (MRI) sequence. The sparse algorithm estimates an optical flow field that represents the motion of contraction during the systole interval.