Chapter 4. Motion Estimation
Motion estimation refers to estimating 2D image-plane motion (correspondence or optical flow) or 3D motion (object motion or pose). It is a fundamental problem in video processing (motion-compensated filtering/compression) and computer vision.
Video is a time-varying two-dimensional (2D) spatial-intensity pattern that is formed by projecting a three-dimensional (3D) dynamic scene into a 2D image plane. Temporal variations in the 2D intensity pattern are usually due to relative 3D motion between a camera and objects in the scene. This chapter presents 3D models (in most cases, simplistic ones) for relative motion between a camera and a rigid (static) scene and 2D models for temporal variations of spatial-intensity ...
Get Digital Video Processing, Second Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
