论文部分内容阅读
分数维作为一种图像纹理特征常用于遥感图像分类,提高图像分数维的测量有助于提高遥感分类精度。本文在介绍目前常用的基于分形布朗运动分数维计算方法的基础上,运用分形的相关理论,指出了现有方法存在的缺陷,提出了改进的分数维计算方法;并用SPOT全色影像中常见的5种地物进行了对比实验,实验结果表明,本文提出的改进方法获得的分数维测量结果比现有的方法更接近理论分析结果,更有利于地物的识别与分类。
As an image texture feature, fractal is often used in remote sensing image classification, improving the measurement of fractal dimension helps to improve the remote sensing classification accuracy. In this paper, based on the commonly used fractal calculation method based on fractal Brownian motion, the fractal theory is used to point out the shortcomings of existing methods and to propose an improved fractal calculation method. Five kinds of ground objects were compared with each other. The experimental results show that the improved method proposed in this paper is closer to theoretical analysis than the existing methods, which is more conducive to the recognition and classification of objects.