基于仿射变换模型的图像配准中的平移、旋转和缩放

Translation, rotation and scaling changes in image registration based affine transformation model

文中讨论了二维仿射变换的平移、旋转和缩放等特性。对可见光波段和红外波段图像采用基于特征的配准 ,以边界作为特征进行相关运算 ,求出边界对应位置的关系 ,建立仿射变换模型 ,按照最大相关原则自适应确定最佳配准参数k、θ、Δx和Δy ,能够实现图像的自动配准。并利用实际可见光与红外图像给出了运用仿射变换模型的实验结果 ,表明该模型可有效解决图像配准中的平移。

In this paper, translation, rotation and scale properties of 2\|D affine transformation are discussed. Visual and IR image registration require a feature\|based apporach. Establishing affine transformation and extracting edge points as feature, this method calculates the cross\|correlation between edges and searches out the relation of corresponding edge points. The maximum correlation principle is involved to adaptively determine the optimal registration parameters k、θ、Δx and Δy . Experimental results using real visual/IR sensor image are presented. It is shown that this model is effective in image registration.