Contextual Patterns Discovery in Post Disaster Evolution of 2011 Japan Tsunami Using TSX Products

This poster proposes a post disaster evaluation of the damages produced by the tsunami in the Tohuku-oki region considering knowledge discovery from TerraSAR-X (TSX) products, by mapping extracted primitive features into semantic classes, thus assuring an interactive technique for productive information mining. Knowledge discovery from Earth Observation images implies mapping low level descriptors (primitive features) extracted from the image into semantic classes in order to provide an interactive method for effective image information mining. In the frame of information theory a communication channel is considered between remote sensing imagery and the user who receives existing information in the data sources, coded as image semantic content. This channel has three components - Data Source Model Generation, Query and Data Mining. Data Source Model Generation uses image content analysis to generate a set of scene’s content descriptors. Further, the Query component involves the user and performs an image retrieval based on image content as query parameter. The query component relies on the Support Vector Machine classifier which is able to group descriptors into relevant semantic classes. The classifier supports rapid mapping scenarios and interactive mapping. The envisaged data mining process includes three stages: data annotation, data query and quantitative analysis of the results.The Data annotations step considers dataset description, data preparation and data classification in order to perform user annotations. Some query examples considering several scenarios include: Assessment of the transportation infrastructures, highrisk of broken roads caused by damaged bridges, debris detection, assessment of aquaculture areas, and possible energy loss due to the damaged high voltages poles or assessment of agriculture areas, damaged crops and estimation of losses