Road Extraction from Remote Sensing Image Based on Multi-resolution Analysis

In the paper, we present an approach of multi-resolution analysis to extract road information from high resolution imagery. Firstly, high resolution imagery is divided into a series of different resolution images. According to the representation characteristics of roads at different resolution, we analyze roads’ geometrical, radiometric, and topological attributes and carry out a variety of processes such as image enhancement, edge detection ,road finding ,tracking and linking. Then most of main roads at different resolution are gradually extracted. After that, the internal relationship between the same roads at different resolution is set up. All extracted roads are generally normalized into initial resolution to be performed data fusion for eliminating wrong roads and adding miss ones. Thus main roads are correctly extracted. Finally, an example of test is presented in which shows that the exploratory approach is applicable to high resolution road extraction but needs further improvements.