ABSTRACT
This chapter provides a general characterization for two-dimensional (2-D) motion estimation and different classifications of various methods for 2-D motion analysis in a wider scope. It is concerned with a performance comparison among the three major techniques. The chapter presents different classifications of various methods in the three major 2-D motion estimation techniques: block matching, pel-recursion, and optical flow. The aperture problem describes phenomena that occur when observing motion through a small opening in a flat screen. With the pel-recursive technique, say, the steepest descent method, conservation information is the intensity of the pixel for which the displacement vector is to be estimated. The problems of occlusion and disocclusion make motion estimation more difficult and hence more challenging. There are two types of motion: rigid motion and nonrigid motion. Most cases in computer vision are concerned with rigid motion. The chapter analyses nonrigid motion estimation and addresses its relevance in visual communications.
