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

• Antragsteller: Professor Dr.-Ing. Christian Heipke
• Fachliche Zuordnung: Geodäsie, Photogrammetrie, Fernerkundung, Geoinformatik, Kartographie
• Förderung: Förderung von 2005 bis 2008
• Projektkennung: Deutsche Forschungsgemeinschaft (DFG) - Projektnummer 5456485

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.

• DFG-Verfahren: Sachbeihilfen
• Internationaler Bezug: China
• Beteiligte Person: Renliang Zhao