HSI空间中基于自适应阈值的彩色地图的道路提取  

Road Extraction From Color Map Based on Adaptive Threshold Algorithm in HSI Space

作　　者：张璐璐[1] 何宁[1] 徐成[1] 王金宝[1] 

机构地区：[1]北京联合大学北京市信息服务工程重点实验室,北京100101

出　　处：《北京联合大学学报》2014年第3期14-19,共6页Journal of Beijing Union University

基　　金：国家自然科学基金资助(61270120;61370138);2014年"启明星"大学生科技创新项目(201411417SJ053)

摘　　要：目前地理信息系统的应用非常广泛,其中,电子地图中道路网的提取是目标识别中重要的研究内容之一。提出了一种基于彩色理论的自适应阈值道路提取方法,首先将图像从RGB空间转换至HSI空间后,利用自适应阈值的方法对图像进行分割,并对分割结果进行了平滑和增强的后处理,最后利用数学形态学的相应方法对目标进行提取。将该方法应用于北京的电子地图图像进行道路目标的提取,得到了很好的效果。Road extraction from electronic map is an important task which is relied on Geographic Information System（ GIS） recently. It has a very wide range of applications on target recognition research. This paper proposes a method about adaptive threshold which is based on color theory. First to convert the image from RGB space to HSI space,it will do the image segmentation with the method of adaptive threshold,then do postprocessing on the segmentation result,such as smoothing and enhancing. Finally it uses corresponding method of mathematical morphology to extract target. The method has been applied to electronic maps of Beijing area,and it could extract the road clearly and obtain a good effect.

关 键 词：自适应阈值 道路提取 HIS空间 去噪 数学形态学 

分 类 号：P208[天文地球—地图制图学与地理信息工程]