一种准自动高精度图像配准算法

A Semiautomatic High-accuracy Algorithm for Image Registration

为了增强图像配准的鲁棒性,提出了一种人机交互的图像配准算法,该算法首先利用人工选择控制点的方式得到变化模型的初始参数,然后利用初始参数寻找其他可能匹配的特征点对,最后利用加权最小二乘法精确求解变化模型的参数,并完成图像的配准。该算法不仅降低了计算量,而且减少了误配的可能性,并且对灰度差异较大的图像也是适用的。大量实验表明,提出的方法对同种传感器或者不同传感器图像之间的配准都是有效的。

A semiautomatic algorithm for image registration is presented for increasing the robustness of image registration. We first compute rude model parameters by choosing some corresponding points manually,then finding other points that approximately match each other from the feature points, finally,compute the precise parameters using weighted least - square method. This algorithm decreases the possibility of false registration as well as the computer complexity. The experiment result tested by images from either the same sensor or different sensors is shown that the proposed algorithm for registration is accurate and effective.