Fusion of imaging and nonimaging sensor information for airborne surveillance

Abstract

This paper presents results from an Adaptable Data Fusion Testbed (ADFT) which has been constructed to analyze simulated or real data with the help of modular algorithms for each of the main fusion functions and image interpretation algorithms. The results obtained from data fusion of information coming from an imaging Synthetic Aperture Radar (SAR) and non-imaging sensors (ESM, 1FF, 2-D radar) on-board an airborne maritime surveillance platform are presented for two typical scenarios of Maritime Air Area Operations and Direct Fleet Support. An extensive set of realistic databases has been created that contains over 140 platforms, carrying over 1 70 emitters and representing targets from 24 countries. A truncated Dempster-Shafer evidential reasoning scheme is used that proves robust under countermeasures and deals efficiently with uncertain, incomplete or poor quality information. The evidential reasoning scheme can yield both single ID with an associated confidence level and more generic propositions of interest to the Commanding Officer. For nearly electromagnetically silent platforms, the Spot Adaptive mode ofthe SAR, which is appropriate for naval targets, is shown to be invaluable in providing long range features that are treated by a 4-step classifier to yield ship category, type and class. Our approach of reasoning over attributes provided by the imagery will allow the ADFT to process in the next phase (currently under way) both FUR imagery and SAR imagery in different modes (RDP for naval targets, Strip Map and Spotlight Non-Adaptive for land targets).

Exploitation of a priori knowledge for information fusion

“…These are further detailed in the sub-sections below as well as in [4][5][6]. 1. maximum acceleration, both tangential (if available for aircraft, it denotes the likely presence of afterburners) and centrifugal (with higher g values likely denoting a fighter aircraft), 2. maximum platform speed (the quoted value is relevant to static ambient atmosphere and must be interpreted, or fuzzified, to account for air currents, particularly when the aircraft can reach the jet stream), 3. minimum platform speed, e.g.…”

Multisensor fusion effects on the characterization and optimization of TPED architecture performance

“…2 The term 'soft' is used by fusion analysts to mean estimates on the confidence in declaring a target to be of a specific type and/or other types, rather than simply a 'hard' declaration without an associated confidence measure. 3 We considered the use of two archives -one for storing the latest 'fused' results on a target and a second for storing all incoming sensor reports in case one needs to disregard reports generated by a particular source at a later time. This would accommodate cases when a source is later known to provide bad information, and hence allow fusion of results omitting the faulty data.…”

Information fusion measures of effectiveness (MOE) for decision support

“…To facilitate target tracking and ID results [45] for decision support requires efforts in fusing imaging and non-imaging data [46,47], understanding the user's needs [48], the theoretical and knowledge models [49], and situational awareness processing techniques [50]. In a dynamic scenario, resource coordination [51] is needed for both context assessment, but also the ability to be aware of impending situational threats [52,53].…”