SAHARA Semi-Automatic Help for Aerial Region Analysis

Sahara is a WEU funded project. Its aim is to show the potential usefulness of image interpretation techniques to help photo-interpreters. Typically, this could include drawing a sketch of the airport, looking for changes with respect to a reference geographic database, etc. The need for tools that fasten satellite imagery interpretation will become even more stringent with the next generation of satellites that will provide a very high amount of high resolution data. We therefore used aerial multi-sensor imagery with resolution expected in the near future for commercial satellite imagery (VIS 2m, SAR 5m, etc.). As a test case, the project was dedicated to the interpretation of airports. In this scope the main objects of interest like runways, taxiways, shelters, airplanes and buildings are searched for. In this paper, we show that object-related detectors are not able to solve the problem by their own. We then propose a scheme in which high level knowledge may be introduced in an efficient way. This knowledge is used to steer the interpretation and to enforce a coherent result. A GUI allows the user to follow the evolution of the interpretation and to have a clear view of the high level knowledge that is used. The user may also intervene at any moment to help the interpretation, by correcting errors, stopping the research in a non promising areas, etc.