摘要
本文讨论了对一般目标图像的对准方法,采用仿射变换模型,舍弃借助迭代法搜索图像最佳配准参数的传统方式,使用推导公式一步计算图像的平移旋转参数。该公式运用仿射变换单应矩阵最小二乘运算模型推导所得,首次得到可单步计算目标图像与待对准图像对位参数的计算算法,大大提高运算效率,实现了实时对位的功能,最后通过实验验证算法的有效性。
Trying to provide a more effective algorithm for real-time counterpoint and alignment in the image,we propose an estimate method using affine transformation modal to calculate image translation rotation parameters,which is different from the traditional iteration method in searching image.It's the first time to provide the algorithm which can calculate target and alignment image registration parameter by single step,using the model of the least square of the affine transformation homography.And the effectiveness of this algorithm is validated through the corresponding experiment.
出处
《光电工程》
CAS
CSCD
北大核心
2016年第4期61-65,共5页
Opto-Electronic Engineering
基金
广州市科技计划项目(2014J4100205
2014J420081)资助课题
关键词
图像对准
仿射变换
平移
旋转
单应矩阵
alignment
affine transformation
translation
rotation
homography