Please use this identifier to cite or link to this item:
|Title:||ESA-EUSC-JRC 2011 - The proceedings of the Seventh Conference on Image Information Mining: Geospatial Intelligence from Earth Observation|
MARCHETTI Pier Giorgio
|Publisher:||Publications Office of the European Union|
|Other Identifiers:||EUR 24762 EN|
|Abstract:||Today the analysis of a few, very high resolution, multi-spectral images and Synthetic Aperture Radar (SAR) can be complex and challenging. In addition, the emerging needs from major applications (e.g.: mapping, global monitoring, disaster management support, non proliferation, etc.) and large programmes / initiatives (e.g.: GEMS, GEO, GEOSS), and the continuous increase in archives' size and EO sensors' variety, require new methodologies and tools for information mining and management, supported by shared knowledge. The manual process performed by experts to mine information from images is currently too complex and expensive to be applied systematically on even a small subset of the acquired scenes. This limits the full exploitation of the petabytes of archived or new data. The issue might become even more challenging in future since more missions - including constellations - are being planned, with broader sensor variety, higher data rates and increasing complexity. As an example, ENVISAT, Sentinels 1 and 2, or the ESA third party missions. Since the problem are common to other fields, contributions from multimedia, medicine, astronomy, etc.are also expected. Results from current R&D activity might ease the access to the imagery (today mostly retrieved using spatio-temporal and a few more attributes) also through their information content. The need to access information also in large volumes of image data has stimulated the research in the field of content-based image retrieval during last decade. Many new concepts have been developed and prototyped. However the dramatic increase in volume, details, diversity and complexity, and the user demand for simultaneous access to multi-domain data urgently require new approaches for image information mining, multi-domain information management, and knowledge management and sharing (in support of information mining and training). This year's conference continues to focus on automation in support of applications and services for geospatial intelligence, for which Image Information Mining is considered of very high interest and appropriate. This theme proves most successful when cross-cued from other intelligence disciplines, therefore the conference topics are broadened towards more generic Information Mining. In addition, because the future will be marked by an explosion of satellite imaging missions, the conference is expected to bring new stimulating ideas, concepts or methods also for the use of multi-temporal images. These include for example recent developments in mathematical morphology related to hierarchical representations based on constrained connectivity, morphological profiles based on arbitrary attributes, structural based change detection coupled with mutual information analysis, and the use of eye-tracking devices for humancomputer interaction. Robust estimation and Bayesian methods as model selection or hierarchical models in relation with the information transmission theory, for accessing and communicating the content of data missives, and advanced methods derived from the Kolgomorov complexity theory, and their applications for data and image modeling for spatio-temporal data mining is the i.e. discovering relevant and previously not known patterns from large spatiio-temporal datasets. Advanced methods in raster database system and their integration with semantics systems to discover, access, and retrieve the content of EO and other related data. User relevant image contents and associated meta-data descriptors, as base for automated annotation and visual data mining. This report is a collection of peer-reviewed papers presented|
|JRC Institute:||Institute for the Protection and Security of the Citizen|
Files in This Item:
There are no files associated with this item.
Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.