Mining Spatio-Temporal Metadata for Satellite Images Interpretation

Mining the growing data issued from the interpretation of remotely sensed images to obtain the necessary information for land cover change studies becomes more difficult and makes the data volume problem particularly acute. Mitigating this problem requires using data efficiently as metadata for mining and selecting appropriate data for change studies. In this paper, we propose an integrate hierarchical approach based on the use of a blackboard architecture and multi-agent system and having a reasoning ability to find the best strategy to extract and create metadata about extracted objects. This architecture models relation-ship between objects and primitives extracted from images as metadata and use a transition diagram to handle temporal dependencies and perform the detection of temporal changes of objects. We validate our approach on a set of multi-temporal Spot images, to model the evolution of detected object.