论文部分内容阅读
提出了一种基于对比度增强和形态学的遥感影像道路边界与特征点提取的方法。先对遥感影像进行对比度变换增强,通过对比分析直方图均衡化和对比度分段线性增强两种方法获取的增强影像,选取区分度大的分段线性增强方法进行影像增强,然后运用数学形态法进行影像分割,实现道路和其他图像信息的有效分离。利用Krisch算子进行边缘检测提取道路的边缘信息,并基于边缘特征利用改进的Harris算子提取特征点,将提取的特征点进行拟合并用函数模型描述图像道路信息,用于后期制图中道路信息的矢量化。
A method based on contrast enhancement and morphological remote sensing image road boundary and feature point extraction is proposed. Firstly, the contrast of the remote sensing image is enhanced. By comparing and analyzing the enhancement images obtained by histogram equalization and contrast piecewise linear enhancement, the piecewise linear enhancement method with high degree of differentiation is selected to enhance the image, and then the mathematical morphology is used Image segmentation, the effective separation of roads and other image information. Krisch operator is used to detect the edge information of the road, and the feature points are extracted based on the edge features by using improved Harris operator. The extracted feature points are fitted and function model is used to describe the image road information, which is used for the road information Vectorization.