The Extraction Of Roads From High Resolution Satellite Remote Sense Images

With the rapidly development of space techniques and information techniques, the high resolution remote sensing satellite can supply human with the digital images of high accuracy and large capability. Target extraction from remotely sensed images has become the important means of the space information updating, and has been used extensively in the national economic production, and it also leads to various new methods of targets extraction. Hence it is very necessary to extract targets especially line targets from remotely sensed images. This paper studies the extraction of roads from remotely sensed images based on mathematical morphology.Mathematical morphology is an applied mathematical branch for the quantitative analysis of spatial structures efficiently based on concepts of shape and structural element. Mathematical morphology has been applied to image, signal processing and geometrics et al. for many applications.Based on mathematical morphology and high-resolution satellite remotely sensed images, this paper developed the following models and algorithms:(1) Various algorithms of mathematical morphology are researched; they include hit or miss Transformation, edge detection and morphological grads, et al.(2) The combination of traditional algorithms and morphological algorithms are used to preprocess the target image. Different target information is obtained by making use of different abutment pixel templates, and the extraction results are compared and analyzed.The experimental results show that it is very effective to apply the methods of mathematical morphology to special target extraction, and it is very important for the GIS data updating ,particularly for those urban areas where ground feature change rapidly.