光流场估计算法的优化分析

Analysis on the Optimization of Optical Flow Estimation Algorithms

运动估计一直是视频处理领域的核心课题之一 ,而基于Horn和Schunk所提出的光流基本约束方程的光流场估计类算法是图像运动估计的一类重要算法。从由于缺少约束而事实上并不完备的光流基本约束方程出发 ,人们提出了各种光流计算方法 ,从算法约束条件上分为全局优化和局部优化两类。本文将对各类算法进行比较 ,归纳出其思路发展轨迹。同时 ,本文将选取一种基于区域平滑约束的光流场估计算法进行分析 ,该算法性能较为稳定 。

Optical Flow Field Estimation Algorithms,one important kind of picture motion estimation as the essential task of video processing,are typically based on the Basic Constraint Equation of Optical Flow Estimation,sponsored by Horn and Schunk,which is in fact not complete due to the lack of enough constraints.Categories of Optical Flow Estimation Algorithms,falling into the two categories of Global Optimizing Algorithms and Local Optimizing Algorithms,have been sponsored and in this paper they are compared and a typical up-to-date instance of them analyzed so that the track of the optimization developing is thus recovered.