基于邻域信息的红外与可见光图像互信息配准

基于互信息的配准方法以其自动化程度高和配准精度高的优点被广泛应用在图像配准中。文中针对红外与可见光图像配准中采用传统的互信息,仅考虑图像像素的灰度信息,而没有考虑图像像素之间空间信息的情况,提出了一种基于邻域信息的互信息配准算法。该算法充分利用图像像素之间的空间信息,在互信息计算中图像中每个像素的灰度值由其邻域像素的灰度值按照距离分配不同的权值共同得到。实验表明该算法使配准曲线更加光滑,配准过程中极值更易找出,提高了配准精度和抗噪能力。

Infrared and Visible Light Image Mutual Information Registration Based on Neighborhood Information

Mutual information which as an effective measure used in image registration.Standard mutual information used in the infrared and visible light image registration only considers the pixels intensity value but ignores their spatial information.In this paper give a new algorithm based on neighborhood information.Every pixel is determined by neighborhood pixel according to weight value by distance in process of the mutual information calculation.The experiment results show that the algorithm makes full use of spatial information, smoothes the registration curve,can easily find extreme value,achieves a high accuracy,and has good performance against noise.