基于Shearlet变换和KPCA的多时相遥感图像变化检测

Change Detection of Multi-temporal Remote Sensing Images Based on Shearlet Transform and KPCA

为了进一步提高多时相遥感图像变化检测的精度,本文提出了一种将Shearlet变换与核主成分分析(kernel principal component analysis,KPCA)相结合用于遥感图像变化检测的算法.首先利用Shearlet变换的多尺度、多方向和各向异性等特点,对遥感图像进行多尺度分解,然后对分解后的数据进行核主成分分析,再进行Shearlet反变换得到含变化信息的图像,最后对该图像利用模糊局部信息C均值(fuzzy local information c-means,FLICM)聚类算法进行分割,实现遥感图像的变化检测.大量试验结果表明,与基于主成分分析(principal component analysis,PCA)、基于KPCA、基于小波变换和PCA 3种变化检测算法相比,本文算法能有效地分离出变化信息,得到更准确的变化检测图像,具有更高的变化检测精度,且对背景有较强的鲁棒性,同时也减少了计算复杂度.

To further improve the accuracy of change detection on multi-temporal remote sensing image, a change detection algorithm based on shearlet transform and kernel principal component analysis（KPCA） was proposed. Firstly, multi-scale decompositions of remote sensing images were performed by using shearlet transform with the characteristics such as multi-scale, multi- direction, anisotropy and so on. Then kernel principal component analysis was carried out on the decomposed data and the image with change information was obtained by inverse shearlet transform. Finally the image was segmented by using fuzzy local information c-means （FLICM） clustering algorithm, thus change detection of multi-temporal remote sensing images was completed. A large number of experimental results show that, compared with the three change detection algorithms such as the algorithm based on principal component analysis （PCA）, the algorithm based on KPCA, and the algorithm based on wavelet transform and PCA, the proposed algorithm can effectively separate change information, get the change detection image with higher change detection accuracy, and has stronger robustness to background, meanwhile the computation complexity is reduced.