[IPAG Home Page] [Publications] [Dissertation Archive] [Personnel]

IPAG Dissertation Archive

Multiframe Estimation of Non-Rigid Motion from Image Sequences

A Dissertation

Presented to the Faculty of the Graduate School


Yale University

in Candidacy for the Degree of

Doctor of Philosophy


John Colin McEachen II

Dissertation Director: James Scott Duncan

May 1996


A robust, flexible system for tracking the point to point non-rigid motion of deformable objects in image sequences has been developed. This system is unique in its ability to model deformations across multiple frames. The foundation of this system is an adaptive transversal filter based on the recursive least-squares algorithm. This filter facilitates the integration of models for periodicity and proximal smoothness as appropriate using a contour-based description of the object's boundaries. The primary motivation for this work is characterization of cardiac left-ventricular (LV) endocardial wall motion. Knowledge of the correspondence between two given frames from an image sequence of the cardiac cycle allows precise description of the associated motion of the heart and measurement of physical parameters that aid in analysis of the heart's dynamics. This is critical in identifying abnormal myocardial contraction in the LV due to heart disease. A set of correspondences between contours and an associated set of correspondence quality measures comprise the input to the system. Two methods of correspondence relative to cardiac motion are examined. The first uses similarity of shape between contour segments as a match metric. The second combines instantaneous estimates of velocity, acquired through phase contrast magnetic resonance (MR) imaging, with the shape matching process. Frame-to-frame relationships from two different frames of reference are derived and analyzed using synthetic and actual images. Two multiframe temporal models, both based on a sum of sinusoids, are derived. Illustrative examples of the system's output are presented for quantitative analysis. Validation of the system is performed by comparing computed trajectory estimates with the trajectories of physical markers implanted in the LV wall. Sample case studies of marker trajectory comparisons are presented. Ensemble statistics from comparisons with 15 marker trajectories are acquired and analyzed. A multiframe temporal model without spatial periodic constraints was determined to provide excellent performance with the least computational cost. A multiframe spatiotemporal model provided the best performance based on statistical standard deviation, although at significant computational expense. Extensions of the system to LV function analysis, tracking motion in surface sequences, and tracking non-rigid motion in neurite growth cones are outlined.

BibTeX Entry

author =  "J. C. McEachen II",
title  =  "Multiframe Estimation of Non-Rigid Motion from Image Sequences",
school =  "Yale University",
month  =  "May",
year   =  "1996")

Questions regarding the content of this page should be directed to the group director.

Questions or bug reports regarding this interface should go to webmaster@noodle.med.yale.edu.

Home Page, webmaster@noodle.med.yale.edu