TR#344:Motion Estimation and Segmentation Using a Recurrent Mixture of Experts Architecture

Yair Weiss and Edward H. Adelson

To appear:
1995 IEEE Workshop on Neural Nets for Signal Processing
Cambridge, MA

Estimating motion in scenes containing multiple motions remains a difficult problem for computer vision. Here we describe a novel recurrent network architecture which solves this problem by simultaneously estimating motion and segmenting the scene. The network is comprised of locally connected units which carry out simple calculations in parallel. We present simulation results illustrating the successful motion estimation and rapid convergence of the network on real image sequences.