In this letter, we propose an algorithm to detect the presence of forest fires using data from both geostationary and polar-orbiting satellites. The very frequent acquisitions of the Spinning Enhanced Visible and Infrared Imager radiometer placed onboard the Meteosat Second Generation-9 satellite are used as main source for the algorithm, while the MEdium Resolution Imaging Spectrometer global vegetation index and the Advanced Along-Track Scanning Radiometer measurements are used to enhance the reliability of the detection. The problem is approached in a ¿global¿ way, providing the basis for an automated system that is not dependent on the local area properties. In cooperation with the Centre de Suivi E¿cologique (Dakar, Senegal), the proposed algorithm was implemented in a ¿Multisource Fire Risk Management System¿ for the Senegal area, as briefly described in this letter. A field campaign of one week was carried out in order to perform a validation of the system's detections, showing a good agreement with the fire coordinates measured on the ground. Furthermore, a consistency check was performed using data from the Moderate Resolution Imaging Spectroradiometer (MODIS) Rapid Response System, showing that more than 76% of high-confidence MODIS events are detected by the algorithm.

In this paper, we demonstrate the concepts of a prototype of a knowledge-driven content-based information mining system produced to manage and explore large volumes of remote sensing image data. The system consists of a computationally intensive offline part and an online interface. The offline part aims at the extraction of primitive image features, their compression, and data reduction, the generation of a completely unsupervised image content-index, and the ingestion of the catalogue entry in the database management system. Then, the user's interests-semantic interpretations of the image content-are linked with Bayesian networks to the content-index. Since this calculation is only based on a few training samples, the link can be computed online, and the complete image archive can be searched for images that contain the defined cover type. Practical applications exemplified with different remote sensing datasets show the potential of the system.

No abstract available.

This paper addresses the methodological aspects of designing a semantic association function in a hypertext information retrieval environment and model. Through this function a part of an associative information retrieval model is designed and implemented. Initially the paper provides reference to previous efforts in associative information retrieval and automatic search formulation and re-formulation operations. The semantic association function is a function which belongs to a new functional hypertext information retrieval model that has been previously justified and presented. For this reason, the meaning and aim of the semantic association function are also recalled and reported. The central part of the paper presents motivations and justification for the design and implementation of the semantic association function in an experimental hypertext information retrieval interface as opposed to a traditional online information retrieval system.

In this paper, we propose a method for specifying the functionality of an intelligent interface to large-scale information retrieval systems, and for implementing those functions in an operational environment. The method is based on a progressive, three-stage model of intelligent information support; a high-level cognitive task analysis of the information retrieval problem; a low-level specification of the host system functionality; and, derivation of explicit relations between the system functions and the cognitive tasks. This method is applied, by example, in the context of the European Space Agency Information Retrieval Service, with some specific suggestions for implementation of a stage one intelligent interface to that system.