基于对比度增强和形态学的遥感影像道路提取

发布时间：2018-06-18 19:34

  本文选题：对比度增强 + 数学形态学　； 参考：《测绘通报》2017年08期

【摘要】：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。
[Abstract]:A method for extracting road boundary and feature points from remote sensing image based on contrast enhancement and morphology is proposed. First, contrast transform enhancement of remote sensing image is carried out. The enhancement images obtained by histogram equalization and contrast piecewise linear enhancement are compared and analyzed, and the segmented linear enhancement method with large differentiation is selected for image enhancement. Then the mathematical morphological method is used for image segmentation to realize the effective separation of road and other image information. The edge information of road is extracted by Krisch operator. Based on the edge feature, the feature points are extracted by improved Harris operator, and the extracted feature points are combined to describe the road information of the image using function model. Used for vectorization of road information in late cartography.
【作者单位】： 信息工程大学;河南理工大学;
【基金】：国家自然科学基金(41271391)
【分类号】：TP751
，

本文编号：2036629