Measurement of Image Velocity / Edition 1

by David J. Fleet

Overview

Measurement of Image Velocity presents a computational framework for computing motion information from sequences of images. Its specific goal is the measurement of image velocity (or optical flow), the projection of 3-D object motion onto the 2-D image plane.
The formulation of the problem emphasizes the geometric and photometric properties of image formation, and the occurrence of multiple image velocities caused, for example, by specular reflections, shadows, or transparency. The method proposed for measuring image velocity is based on the phase behavior in the output of velocity-tuned filters. Extensive experimental work is used to show that phase can be a reliable source of pure image translation, small geometric deformation, smooth contrast variations, and multiple local velocities. Extensive theorectical analysis is used to explain the robustness of phase with respect to deviations from image translation, and to detect situations in which phase becomes unstable. The results indicate that optical flow may be extracted reliably for computing egomotion and structure from motion.
The monograph also contains a review of other techniques and frequency analysis applied to image sequences, and it discusses the closely related topics of zero-crossing tracking, gradient-based methods, and the measurement of binocular disparity. The work is relevant to those studying machine vision and visual perception.

Product Details

ISBN-13:	9780792391982
Publisher:	Springer US
Publication date:	03/31/1992
Series:	The Springer International Series in Engineering and Computer Science , #169
Edition description:	1992
Pages:	203
Product dimensions:	6.10(w) x 9.25(h) x 0.24(d)

Table of Contents

I Background.- 1 Introduction.- 2 Time-Varying Image Formation.- 3 Image Velocity and Frequency Analysis.- 4 Velocity-Specific Representation.- 5 Review of Existing Techniques.- II Phase-Based Velocity Measurement.- 6 Image Velocity as Local Phase Behaviour.- 7 Experimental Results.- 8 Computing 2-D Velocity.- III On Phase Properties of Band-Pass Signals.- 9 Scale-Space Phase Stability.- 10 Scale-Space Phase Singularities.- 11 Application to Natural Images.- IV Conclusions.- 12 Summary and Discussion.- Appendices.- A Reflectance Model.- B Proof of an n-D Uncertainty Relation.- D Additional Experiments.

Editorial Reviews

Presents a computational framework for computing motion information from sequences of images in order to measure the image velocity (or optical flow), and project the motion of a three-dimensional object onto a two-dimensional image plane. The method described emphasizes the geometric and photometric properties of image formation, and is based on the phase behavior in the output of velocity-tuned filters. Many of the photographs of screen images are of too poor a quality to be informative. For professionals in machine vision and visual perception. Annotation c. Book News, Inc., Portland, OR (booknews.com)

Booknews