Technical Survey and Forecast for Information Fusion

This paper summarizes the results of a study forecasting the development of information fusion technology over the next 20 years [1]. The study was carried out on behalf of the Swedish Armed Forces, as part of an effort to estimate future developments in some technology areas of high relevance for the development of a Network-Based Defence system. 1.0 INTRODUCTION Information fusion is still in the research stage and it is not yet clear how its basic methodology should be structured. The study describes the current situation based on a thorough and critical analysis of the open research literature. Based partly on published assessments by other authors, partly on the author's own experience, an estimate is then made of the likely progress in this area over a 10 and a 20 year period. The combined effect of rapid technical development in sensor technology, the establishing of new communication technologies globally, and the literally exploding improvement of the price-performance ratio for computer systems, forms the technological background of the efforts by a growing number of nations to create a Network-Based Defence (NBD). This move towards NBD implies that military decision makers will receive an ever increasing information flux to try to cope with. Information fusion is about providing support in the task of weighing together and interpreting this information, i e, to instantiate, perhaps even build, good models of a complex, uncertain reality more or less in real time. New and rapidly improving capabilities to automatically collect large sets of data, and to move large sets of data across communication networks, have raised new questions regarding opportunities to automatically sort, classify, and interpret data to form an operational picture. In this process, data from various sources are used: sensor data, as well as data on probable behavioral patterns of the opponent, cultural and geographic characteristics of the area of operations, etc. Such data have previously been fused to an operational picture through time-consuming manual analyses and discussions. As the availability of sensor data explodes as a result of technological advances, this manual fusion process becomes a bottleneck when establishing the operational picture. If sensor data can not be processed and automatically Paper presented at the RTO IST Symposium on “Military Data and Information Fusion”, held in Prague, Czech Republic, 20-22 October 2003, and published in RTO-MP-IST-040. RTO-MP-IST-040 4 1 Report Documentation Page Form Approved OMB No. 0704-0188 Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. 1. REPORT DATE 00 MAR 2004 2. REPORT TYPE N/A 3. DATES COVERED 4. TITLE AND SUBTITLE Technical Survey and Forecast for Information Fusion 5a. CONTRACT NUMBER