Automatic quality assessment and update of digital road data in sub-urban areas using digital aerial images

使用数字航空图像自动评估和更新郊区数字道路数据

• 批准号: 5456485
• 负责人: Professor Dr.-Ing. Christian Heipke
• 金额: --
• 依托单位: Institut für Photogrammetrie und GeoInformation (IPI)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2005
• 资助国家: 德国
• 起止时间: 2004-12-31 至 2007-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/5456485?language=en
• 关键词: Automatic; quality; assessment; update; digital

In this project wie will develop novel, geometric-topologic and statistical methods fpr an automatic quality assessment and update of existing geo-spatial data. The necessary reference information will be derived from up-to-date digital aerial images via automatic image analysis. As an example for geo-spatial data we have selected roads in sub-urban areas. In contrast to existing approaches for quality control of road data, we will - for the first time - carry out a common and consistent modelling and processing of the road data to be assessed and the road objects extracted from the images. For this task we will set up a geometric-topologic relationship model for the roads and their surroundings, the statistical procession is based on the so called Hint-Theory. As compared to other approaches the Hint-Theory has the major advantage that not only prior knowledge can be modeled, an explicit modelling of ignorance is also possible. In this manner we expect to develop efficient and reliable algorithms for our task. This project will use German ATKIS BasisDLM data as an example. The transfer of the methods to be developed to similar, foreign data sets is possible without any problems.

在这个项目中，WIE将开发新的几何拓扑学和统计学方法，对现有的地理空间数据进行自动质量评估和更新。必要的参考信息将通过自动图像分析从最新的数字航空图像中获得。作为地理空间数据的一个例子，我们选择了郊区的道路。与现有的道路数据质量控制方法不同，我们将首次对要评估的道路数据和从图像中提取的道路对象进行通用和一致的建模和处理。为此，我们将建立道路与周围环境的几何-拓扑关系模型，其统计处理是基于所谓的暗示理论。与其他方法相比，暗示理论的主要优点是不仅可以对先验知识进行建模，而且还可以对无知进行显式建模。通过这种方式，我们希望为我们的任务开发高效和可靠的算法。本项目将以德国ATKIS BasisDLM数据为例。将待开发的方法转移到类似的外来数据集是可能的，没有任何问题。