一种高分辨率彩色遥感影像的道路检测方法

提出了一种采用FLD特征抽取分类和形状特征相结合的道路检测方法。首先,对标记的样本进行颜色信息的抽取;其次,利用Fisher线性判别对抽取的信息进行遥感影像特征分类,将影像分为道路和非道路两类;然后根据分类结果进行阈值分割检测初步道路网;最后利用道路的形状特征和形态学处理去除误提的信息优化检测结果。实验证明,该方法可以实现具有颜色信息的遥感影像主干道路的检测。

A Method for Road Detection from High Resolution Color Remote Sensing Image

In this paper, a road extracting method is proposed by combining FLD feature extraction and shape fea-ture. This method has four main steps. Firstly, the color information of labeled samples is extracted. Then, fisher linear discriminant is used to implement feature classification to segment the images into two categories: road and non-road, according to the information extracted before. After that, initial road network is extracted by threshold segmentation according to the result of classification. Finally, the road shape optimization features and morphologi-cal processing are used to remove erroneous extraction and optimize the extraction results. Experiment results show that the proposed method can realize the main road extraction from the remote sensing image with color information.