期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2007
卷号：XXXVI-4/W54
页码：147-152
出版社：Copernicus Publications
摘要：Updating of navigation databases is an important task to ensure a high level utilization of navigation data. For example, in fundamental topographic databases roads are often represented as a single line without detailed connectivity and traffic flow information, but for a navigation database, roads separated by physical barriers should be represented as two roads with different traffic flow directions. Updating navigation database of this kind is mainly carried out by field investigation at present. In this paper, we present a process integrating high resolution satellite imagery with a national fundamental topographic database for updating of navigation data. This paper presents the first step of our work focused on the physical barriers consisting of vegetation. Firstly, road information in the topographic database is used to select corresponding areas in the image. Secondly, the Burns algorithm is adopted for extracting directional edge segments. The next stage is detecting two parallel straight edges by Hough Transform, as physical barriers consisting of vegetation can be described by two anti-parallel edges. Some constraints on edge width and intensity are used for the final recognition of the objects. Some results of tests show the applicability of the proposed method
关键词：Update; Navigation; GIS; High Resolution; Database; Edge Detection
