Image information mining : exploration of Earth observation archives

[摘要] The new generation of high resolution imaging satellites acquires huge amounts of data which are storedin large archives. The state-of-the-art Systems for dataaccess allow only queries by geographical location,time of acquisition or type of sensor. This informationis often less important than the content of the scene,i.e. structures, objects or scattering properties. Meanwhile,many new applications of remote sensing dataare closer to Computer vision and require the knowledge of complicated spatial and structural relationshipsamong image objects.

We are creating an intelligent satellite informationmining system, a next generation architecture to helpusers to rapidly collect information, a tool to enhanceand to manage the huge amount of historical andnewly acquired satellite data-sets by giving expertsaccess to relevant information in an understandableand directly usable form and to provide friendly interfaces for information query and browsing.

Research topics are within the frame of Bayesianlearning, content-based querying, data modelling andadaptation to user conjecture.

[学科分类] 自然科学（综合）