摘要
在基于灰度相关的图像匹配算法中，归一化互相关（Ncc）匹配算法是常用的匹配算法，但算法复杂、匹配时间长是制约其应用的主要原因。本文提出一种基于自适应步长选择的NCC匹配算法，根据归一化互相关系数自适应地选择搜索步长，加快了匹配速度；改进归一化互相关系数算子，增加了步长选择阈值的区分度，提高了自适应选取步长的精确度，实现了匹配时间和匹配精度的合理分配。实验表明，该算法在保证匹配精度的同时，匹配时间缩短为传统NCC算法的10％～50％。
Normalized Cross Correlation （NCC） algorithm is one popular image matching algorithm based on the intensity correlation, but its application is limited because of high computational complexity and long computing time Therefore, a normalized cross correlation image matching algorithm based on adaptive step size is proposed. According to the normalized cross correlation coefficient, the step size is chosen adaptively which can increase the matching speed obviously. The normalized cross correlation coefficient is improved to increase the differential degree of step size thresholds. So the selection precision of adaptive step size is boosted evidently. At the same time, the matching time and the matching speed are allocated reasonably. Experiment results indicate that the matching time of the proposed algorithm is reduced to 10%-50% compared with the traditional NCC algorithm without loss of precision .
出处
《光电工程》
CAS
CSCD
北大核心
2013年第10期77-84,89,共9页
Opto-Electronic Engineering
基金
国家自然科学基金项目(61007012)
国家科技支撑计划项目(2012BAF07B05-3)
浙江省重点科技创新团队项目(2010R50028)
关键词
图像匹配
归一化互相关
自适应步长选择
映射函数
区分度
image matching
normalized cross correlation
adaptive step size selection
mapping function
differential degree
