Summary: Estimating Piecewise-Smooth
Optical Flow with Global Matching
and Graduated Optimization
Ming Ye, Robert M. Haralick, Fellow, IEEE, and
Linda G. Shapiro, Fellow, IEEE
Abstract--This paper presents a new method for estimating piecewise-smooth
optical flow. We propose a global optimization formulation with three-frame
matching and local variation and develop an efficient technique to minimize the
resultant global energy. This technique takes advantage of local gradient, global
gradient, and global matching methods and alleviates their limitations.
Experiments on various synthetic and real data show that this method achieves
highly competitive accuracy.
Index Terms--Optical flow, motion discontinuity, occlusion, energy minimization.
OPTICAL flow is a 2D image motion measure that has a wide range
of applications in computer vision , video coding  and
computer graphics . Its accurate and efficient estimation is a
long-standing difficult problem.
The fundamental assumption enabling optical flow estimation