A method for Road detection from high resolution Color Remote Sensing Image

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