Performance evaluation of ATOMI system for road database updating from aerial film, ADS40, Ikonos and Quickbird orthoimagery

Abstract

Automated road extraction from images has drawn considerable attention for decades due to the need for the efficient acquisition and updating of road data for geodatabases. The development of new digital aerial sensors and high-resolution satellite sensors signifies a revolutionary change in image acquisition and the possibility of fully digital processing from image acquisition to the generation of value-added products for various applications. At ETH Zurich in cooperation with and funded by the Swiss Federal Office of Topography (swisstopo), we have developed an operational system for the automated extraction of 3D road networks from imagery that integrates the processing of colour image data and existing digital spatial databases. The system focuses on rural areas, can use stereo or orthoimages and can determine 3D road axes, and other road attributes if the roads have a minimum width of ca. 3 pixels. If no road database exists, it can be generated from scratch, using manual measurement of characteristic road seed points. The system has been extensively tested, mainly by swisstopo, on areas with diverse terrain relief and landcover types using different resolution stereo and orthoimages with good results. Tests have also been performed using ADS40, IKONOS and Quickbird data. This paper reports on the performance evaluation of the ATOMI system using different sensor data in two varying test sites. The test results were qualitatively and quantitatively analysed using accurate reference data. Visual analysis and quantitative measures of accuracy, correctness and completeness are presented, with typical completeness and correctness values of over 90% and planimetric accuracy of 0.4 m to 1 m. The advantages and disadvantages using different sensor data for road network updating are also discussed.