PERFORMANCE OF OPTICAL-FLOW TECHNIQUES

被引:3205
作者
BARRON, JL [1 ]
FLEET, DJ [1 ]
BEAUCHEMIN, SS [1 ]
机构
[1] QUEENS UNIV,DEPT COMP SCI,KINGSTON K7L 3N6,ON,CANADA
关键词
D O I
10.1007/BF01420984
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
While different optical flow techniques continue to appear, there has been a lack of quantitative evaluation of existing methods. For a common set of real and synthetic image sequences, we report the results of a number of regularly cited optical flow techniques, including instances of differential, matching, energy-based, and phase-based methods. Our comparisons are primarily empirical, and concentrate on the accuracy, reliability, and density of the velocity measurements; they show that performance can differ significantly among the techniques we implemented.
引用
收藏
页码:43 / 77
页数:35
相关论文
共 64 条