基于模糊分形特征的遥感图像人造目标检测方法

Man-made target detection in remote sensing image based on fuzzy fractal feature

在分析遥感图像分形特征的基础上,比较了不同分形特征的特点,分析了多种分形特征在对图像背景与人造目标的对应性,讨论了分形拟合误差特征的计算方法,提出了对分形特征量的模糊数学方法描述,研究了基于分形特征的人造目标检测方法。文章选择了多幅含有自然背景和人造目标的遥感图像,应用建议的算法进行综合试验,试验结果表明该方法对检测人造目标是有效的。

Based on the analysis of fractal features of remote sensing image the different characteristics of fractal are compared,and the correspondences between the difference fractal characteristics and the background and man-made object in images are also analyzed.The calculation methods of fractal fitting error feature are given and the fuzzy mathematical description of fractal characteristics are proposed,based on fuzzy fractal features the man-made object detection methods are studied.Several remote sensing images with natural background and man-made objects in it are chosen and tile algorithm proposed in the paper is supplied to process those im- ages. The results show that the method proposed in this paper is valid for detection of man-made objects.