[2005 BOOK] Optical Flow Estimation外文翻译.pdf

This is page 1
Printer: Opaque this
Optical Flow Estimation
David J. Fleet, Yair Weiss
ABSTRACT This chapter provides a tutorial introduction to gradient-
based optical flow estimation. We discuss least-squares and robust estima-
tors, iterative coarse-to-fine refinement, different forms of parametric mo-
tion models, different conservation assumptions, probabilistic formulations,
and robust mixture models.
1 Introduction
Motion is an intrinsic property of the world and an integral part of our
visual experience. It is a rich source of information that supports a wide
variety of visual tasks, including 3D shape acquisition and oculomotor con-
trol, anization, object recognition and scene understanding
[16, 21, 26, 33, 35, 38, 45, 47, 50]. In this chapter we are concerned with
general image sequences of 3D scenes in which objects and the camera
may be moving. In camera-centered coordinates each point on a 3D surface
moves along a 3D path X
(t). When projected onto the image plane each
point produces a 2D path
x(t) ≡(x(t),y(t))T , the instantaneous direction
of which is the velocity d
x(t)/dt. The 2D velocities for all visible surface
points is often referred to the 2D motion field [27]. The goal of optical
flow estimation is pute an approximation to the motion field from
time-varying image intensity. While several different approaches to motion
estimation have been proposed, including correlation or block-matching
(, [3]), feature tracking, and energy-based methods (., [1]), this chap-
ter concentrates on gradient-based approaches; see [6] for an overview and
comparison of the mon techniques.
2 Basic Gradient-Based Estimation
mon starting point for optical flow estimation is to assume that pixel
intensities are translated from one frame to the next,
I(
x, t)=I(
x +
u, t +1), ()
where I(
x, t) is image intensity as a function of space
x =(x, y)T and time
T
t,and
u =(u1,u2) is the 2D velocity. Of course, brightness constancy