基于Contourlet域Krawtchouk矩和改进粒子群的遥感图像匹配

Remote Sensing Image Matching Based on Contourlet-domain Krawtchouk Moments and Improved Particle Swarm Optimization

为了进一步提高遥感图像匹配的精度和运算效率,提出了一种利用Contourlet变换、Krawtchouk矩和改进粒子群的遥感图像匹配算法。在分别对参考图像和目标图像进行Contourlet分解的基础上,引入Krawtchouk矩来提取图像的局部特征,并利用改进的带极值扰动的简化粒子群优化算法对低分辨率的遥感图像进行匹配操作,然后逐级上推,最终实现全分辨率情况下遥感图像的匹配。实验结果表明,该算法与目前常用的遥感图像匹配算法相比,不仅具有更高的匹配精度和运算效率,还有较强的鲁棒性。

To further improve the accuracy and efficiency of remote sensing image matching, an algorithm based on contourlet transform, Krawrchouk moments and improved particle swarm optimization was proposed in this paper. Firstly, the reference image and target image were decomposed to the low resolution image using contoudet transform. Then, the Krawtehouk moments were employed to extract local features of the images. Meanwhile, the extremum disturbed and simple particle swarm optimization was used to match the lowest resolution images. Based on the preliminary result, the matching between the higher resolution images could be implemented stepwise up to the full resolution images. The experimental results show that, compared with those of other existing sensing image matching methods, the proposed algorithm has the high accuracy, efficiency and strong robustness.