基于频谱和空域特征匹配的图像配准算法  

Image Registration Based on Spectral and Spatial Feature Matching

作　　者：陈泽锋 吴庆阳[1,2] 陈顺治 李奇锋 卢晓婷 黄浩涛 Chen Zefeng;Wu Qingyang;Chen Shunzhi;Li Qifeng;Lu Xiaoting;Huang Haotao(College of Electronic Science and Technology,Shenzhen University,Shenzhen,Guangdong 518060,China;College of Big Data and Internet,Shenzhen Technology University,Shenzhen,Guangdong 518118,China)

机构地区：[1]深圳大学电子科学与技术学院,广东深圳518060 [2]深圳技术大学大数据与互联网学院,广东深圳518118

出　　处：《激光与光电子学进展》2020年第2期82-88,共7页Laser & Optoelectronics Progress

基　　金：国家重大科研仪器研制项目(61827815);深圳技术大学启动项目(201723);深圳技术大学校企合作项目(2018010802013)。

摘　　要：针对特征点不明显的图像配准场景,在保证相邻两幅待配准图像重叠面积超过80%的前提下,提出了一种基于频谱和空域特征匹配的配准算法。该算法基于傅里叶频谱图的旋转中心不变性,将空域中两幅图像绕任意一点的旋转角转化成频域中绕频谱图中心的旋转角。利用极坐标系和笛卡尔坐标系的变换关系,将绕频谱图中心的旋转量转化为一维方向的平移量,使用SAD(Sum of Absolute Difference)算法求取旋转角,再使用SAD算法求取平移矩阵。所提配准算法既适用于特征点明显的图像配准场景,也适应于特征点不明显的图像配准场景,且配准精度较高,配准速度较快。Aiming at image registration scenes with inconspicuous feature points,we proposed a registration algorithm based on spectral and spatial feature matching to ensure that the overlapping area of two adjacent images to be registered exceeds 80%.Based on the invariance of the rotation center of the Fourier spectrogram,the rotation angle of the two images in the spatial domain around any point was converted into the rotation angle around the center of the spectrogram in the frequency domain.Using the transformation relationship between the polar and Cartesian coordinate systems,the degree of rotation around the center of the spectrogram was converted into a onedimensional translation,and the rotation angle was obtained using the SAD(Sum of Absolute Difference)algorithm.The SAD algorithm was then applied to determining the translation matrix.The proposed registration algorithm proposed would be suitable for image registration scenes with both inconspicuous and obvious feature points.Moreover,it was characterized by a high speed and registration accuracy.

关 键 词：图像处理 图像配准 傅里叶变换 模板匹配 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]