基于最小生成树的图像融合算法

研究遥感图像融合精度问题。图像融合存在含有冗余和互补信息,造成清晰度降低。针对传统的图像配准算法精度较低,为了提高遥感图像融合的准确度,提出了一种最小生成树遥感图像配准算法,将最小生成树算法应用到图像融合的优化过程中,算法首先提取均匀子采样点集,并在此基础上构造最小生成树,然后使用最小生成树来估计熵,对遥感图像进行配准,最后将图像间的边缘梯度信息融入到融合框架中。算法有效地克服了传统图像融合算法的缺点,仿真结果表明,改进算法有效地提高了图像融合的精确度,并为遥感图像融合提出了有效依据。

Image Fusion Based on Minimum Spanning Tree

The accuracy of remote sensing image fusion problem.Image registration techniques has been widely used in remote sensing images,and other fields,for the traditional image registration algorithm and low efficiency and lack of precision in order to improve the accuracy of remote sensing image fusion,a remote sensing image based on minimum spanning tree registration algorithm,the minimum spanning tree algorithm and the optimization is applied to image fusion process,the algorithm first extracts uniform set of sub-sampling points,and on this basis construct minimum spanning tree,and then use the minimum spanning tree to estimate the entropy,the final image between the edge of the gradient information into the integration framework.Algorithm effectively overcomes the shortcomings of the traditional image fusion algorithms,simulation results show that remote sensing image fusion with traditional algorithm,this algorithm effectively improves the accuracy of image registration to verify the feasibility of the method is an effective The image registration algorithm.