摘要
从高分辨率遥感影像中提取道路信息已有许多研究,但仍存在许多问题有待解决。本文主要研究高分辨率遥感影像上城市道路信息的提取,从四个方面开展,即:遥感影像的预处理、阀值的确定、直线与曲线的提取以及道路信息在原图上的显示。传统的相位编组方法主要针对直线的提取,本文对其进行了改进,得到了一种基于相位编组的半自动提取道路信息的方法。实验中首先结合灰度形态学与Canny算子,得出信息较全的道路边缘轮廓信息,然后根据不同形状的道路模型,运用灰度值参数对相位编组法进行改进,提取出比较准确的道路信息。针对现代城市中常见的立交桥,特别是对其曲率较大的中心部分信息,该提取方法表现出了一定的优越性和适用性,实验结果较为理想。
It is still an open problem to extract road feature from high-resolution remote sensing image, although this topic had been intensively investigated and many methods had been put forwards. All works for this thesis are focused on modern urban road and include the following four steps： image pre-processing, threshold calculation, extraction for straight line and curved line, road information show in the original image. Traditional approach on phase classification has been used to extract straight lines intensively, and in this paper, a new and semi-automatic approach is proposed based on the traditional approach on phase classification. Firstly, basic road network can be obtained from high-resolution remote sensing image based on grey level math- ematical morphology and canny algorithm and then road information can be exactly extracted by means of the ＂grey＂ parameters which can improve the theory of phase-based classification in different kinds of road models. Additionally, to elevate urban highways especially for the curve parts of which, the improved method performs superiorly and suitably. The extracting result is reasonable.
出处
《遥感信息》
CSCD
2008年第4期45-49,60,共6页
Remote Sensing Information
基金
现代工程测量国家测绘局重点实验室开放基金资助项目(ES_SBSM_(07)_09)
863项目:特大城市中心密集区复杂地物群信息的自动提取与定量分析技术(编号:2007AA12Z178)
关键词
道路网络提取
高分辨率遥感影像
特征提取
相位编组
road network extraction
high-resolution remote sensing image
characteristic extraction
phase-based classification
