Improving Cartographic Road Databases by Image Analysis

The extraction of road networks from aerial images is one of the current challenges in digital photogrammetry and computer vision.In this paper, we present our system for 3D road network reconstruction from aerial images using knowledge-based image analysis.In contrast to other approaches, the developed system integrates processing of color image data and information from digital spatialdatabases, extracts and fuses multiple object cues, takes into account context information, employs existing knowledge, rules andmodels, and treats each road subclass accordingly. The key of the system is the use of knowledge as much as possible to increasesuccess rate and reliability of the results, working in 2D images and 3D object space, and use of 2D and 3D interaction when needed.Another advantage of the developed system is that it can correctly and reliably handle problematic areas caused by shadows andocclusions. This work is part of a project to improve and update the 1:25,000 vector maps of Switzerland. The system has beenimplemented as a standalone software package. We tested the system on a number of images in different landscapes. In this paper wepresent the results of our system in recent benchmark tests conducted independently by our project partner in Switzerland, and testresults with black and white images in a test site in Belgium.ISSN:1682-1750ISSN:2194-9034ISSN:1682-177