GNORASI (Coordinator)

GNORASI: Knowledge and processing algorithms data-flow development tool for remote sensing data management. Remote sensing is the acquisition of information about an object or a phenomenon through the use of sensor devices that are not in physical contact with the observed entity. Although it may encompass awide gamut of sensor technologies (e.g. magnetic resonanseimages, ultrasound systems, etc), in its modern usage, the term generally refers to the use of imaging sensor technologies, such as aerial and satellite images. Remote sensing applications have a direct effect on a multidute of public interest services as well as on specialized scientific fields, since they make it possible to collect and analyse critical data that would be otherwise inaccessible and too costly to acquire if collected on the ground. Indicative examples include the creation of maps regarding land usage and conservation, weather forecasts based on the monitoring of meteorological paramenters, research into climate changes, etc.

The opportunities provided through the utilization of remote sensing information for issues concerning agricultural planning, environmental conservation, hazards management including natural disasters and pollution incidents, rural development, etc., render remote sensing applications a critical component in the efforts towards sustainable quality of living and economical growth. As a consequence, the availability of methodologies that enable the systematic interpretation of remote sensing data and advance the automatisation of the involved tasks becomes an urging prerequisite. Eviddently, this prerequisite reflects not only an enganging scientific endeavour, but bears significant industrial implications also, as it will allow for the development of efficacious remote sensing services, in alighment with the needs of the market. The criticality of the situation is further aggravated by the increased awareness and fast take-up of the latest state of the art achievements in remote sensing data recording and analysis that has been witnessed at national level, and which has resulted in a remarkable increase of the volume of data made available.

Aiming to significantly advance the outreach and induce the exploitation of the possibilities offered by remote sensing to officials responsible for administering policies and decision making strategies, as well as citizens towards an improved confrontation of individual matters, “GNORASI” addresses the formalization of the semantic interpretation of remote sensing data through a modular, extensible system that enables the effective combination of knowledge, reasoning and imaging processing algorithms.

Even though notable results have been reported in the literature towards the interpretation of remote sensing data, the existing approaches tend to materialize customised solutions in correspondence with the requirements and specifications posed by individual application scenarios. This inevitably leads to poor extensibility and adaptability properties, while the frequently monolithic implementations that result, raise serious limitations in terms of modularity. As a consequence, the sharing and reuse of the accomplished results is severely hindered, necessitating significant re-engineering in order to address the different requirements featured in a new application context.

Besides inducing additional research strain, the aforementioned weaknesses entail also significant cost in terms of time and resources in order to find the combination of algorithms and methodologies that successfully meets the specifications at hand, before proceeding to its implementation. Moreover, in cases where the applications are characterized by significant variations in the form of the corresponding input and parameters’ data, the algorithms themselves need to be re-designed, restricting further the possibilities for reuse. These afore described weaknesses, namely interoperability, reuse and extensibility encountered in the exsiting knowledge-based approaches to the interpretation of remote sensing data, form the core challenges that “GNORASI” aims to address.

Towards this goal, and in accordance with the relevant initiatives at international level, “GNORASI” targets an integrated, modular framework for the seamless and effective development of remote sensing data interpretation services, by enabling the expert user to select its time the appropriate image processing algorithms and in parallel to define the axiomatic knowledge that underlies the given problem. Thereby, “GNORASI” will support the dynamic development of the suitable per task analysis and interpretation configuration, advocating an open structured, adaptable platform for the systematic definition and combination of image analysis and semantic techonologies.

The combination and coordination of analysis algorithms and corresponding knowledge components services will adhere and be orchestrated through an appropriately defined conceptual framework of reference, so as to ensure the interoperability, extensibility and resue of the constituent analysis algorithms, knowledge structures, and reasoning services. In addition to the investigation of methodologies towards the formalized synergistic utilization of analysis algorithms and reasoning, “GNORASI” also addresses the investigation and research into novel algorithms for remote sensing data analysis, as well as into knowledge modeling and inferencing methodologies, in order to further alleviate limitations challenging the existing state of the art.

As such, the “GNORASI” integrated platform is not yet another remote sensing interpretation system implemented so as to meet the needs of a specific application context (e.g. the recording of burnt land areas or the enumeration of saplings); instead, “GNORASI” suggests a generic and powerful framework that will enable the expert user to effectively put into practice its scientific expertise in an graphical, intuitive fashion either through its interaction with the already existing knowledge repository, i.e. the pool of already introduced  analysis algorithms and knowledge structures, or through the incorporation of new ones.

Through the gradual use of the “GNORASI” platform, experts’ knowledge can be accumulated and made available to new users, providing thereby a continuously growing knowledge repository appropriately equipped to address a wide range of remote sensing applications. This has the additional benefit of allowing the target users to include less experienced ones, as neither programming nor engineering skills are required, as long as the appropriate configuration exists. This adaptability of the proposed system, which is further strengthened by its modular architecture, constitutes a major contribution in scientific much as industrial terms. The availability of a powerful, generic, framework such as “GNORASI” for the development of advanced remote sensing data interpretation services thorugh the effective combination of image analysis and inferencing technologies, paves the way for the industry to develop efficient solutions with respect to the heterogeneous specifications and requirements that characterize the related market.

Finally, although “GNORASI” has a special focus on the interpretation of remote sensing data, commiting a significant part of research efforts into the investigation of novel algorithms for the enhanced analysis of remote sensing data, the coordination and synergistic utilization of analysis algorithms and knowledge technologies constitute a generic framework, independent of domain and application. Consequently, “GNORASI” may aim to further advance the state of the art in the interpretation of remote sensing data, yet, at the same time, it constitutes a generic mechanism, capable of supporting the efficient coupling of image processing algorithms and formal knowledge, in a systematic, formal manner. Thereby, the contribution and expected benefits of “GNORASI” extend the domain of remote sensing and pertain to the generic challenge of coupling formal knowledge in the interpretation process of visual data, and may include fields as diverse as medical imaging, astronomy, automated detection of faulty components in mass production, etc.

Summarising, “GNORASI” aims to advance the current state of the art in research and development of knowledge-based image interpretation applications by providing a generic, modular, platform for the systematic coupling of image processing algorithms and formal knowledge. With a special focus in remote sensing, “GNORASI” aspires to make an essential contribution towards the effective analysis and exploitation of remote sensing information to administration tasks regarding a variety of public interest services related to standard and quality of living, as well as economical growth aspects. Towards this end, the proposed “GNORASI” framework, forming an integrated platform is expected to significantly facilate and advance the efficient development of industrial solutions and support service providers to successfully meet the needs of the market in a profitable way.



  • Kompatsiaris Yiannis (Ioannis)
  • Tsampoulatidis Ioannis