Abstract
An adaptive method for temporal sequence segmentation was developed and its performance assessed in segmentation of cardiac motion image sequences. The primary contribution of this paper is the development of a novel, 2D+time Active Appearance Motion Model (AAMM) that represents the dynamics of the cardiac cycle in combination with the shape and image appearance of the heart. Cootes' 2D Active Appearance Model (AAM) framework was extended by considering a complete image sequence as a single shape/intensity sample. This w ay, the proven strength of AAM's lik e robustness and ability to capture observer preference are augmented with temporal consistency over an image sequence.