一种面向对象的高分辨率影像道路提取方法

高分辨率遥感影像为用户提供了丰富的地表细节信息, 如何利用图像分析技术从高分辨率遥感影像中进行目标提取、更新地理信息数据库, 成为遥感信息处理研究的热点。传统的道路提取方法一般采用像素级检测方法, 仅利用了像素的光谱信息作为道路提取的依据, 无法利用影像的空间信息。提出了一种面向对象的高分辨率卫星影像道路提取方法, 并选取南京市IKONOS 影像进行了实验。首先, 对影像进行分割获取影像对象, 再通过对IKONOS 影像中道路特征的分析, 利用影像对象的光谱特征、几何特征和空间关系建立知识库, 最后, 利用知识库中的规则来提取影像中的道路。实验结果表明采用本方法能够较好地提取出实验区中的道路。

A Method of Road Extraction in High-Resolution Remote Sensing Imagery Based on Object-oriented Image Analysis

High-resolution remote sensing image could provide much detailed information of the surface of the ground.It becomes a hotpot of RS research to use the image analysis methods to fulfill object extraction and update the geography information database.Traditional pixel-level approaches merely utilize the spectral characteristic ignoring the abundant spatial information.An object-oriented method is proposed in this paper: firstly the image is processed by segmentation to attain the image objects,then the knowledge is established according to the analysis of the spectral character,geometry character and the spatial relation of the roads in the image,finally the roads could be extracted by making use of the rules defined in the knowledgebase.We choose the IKONOS image of Nanjing city as experiment data to verify the validity of the proposed method,the experiment result shows that it could obtain better effect compared with the traditional method.