Sensor to shooter information fusion for rapid targeting (SSIFRT)

Abstract

This paper describes the Sensor to Shooter Information Fusion for Rapid Targeting (SSIFRT) program. The objective ofthis program is to design, develop, test, and demonstrate the fusion of intelligence, surveillance, and reconnaissance (TSR) data with on-board sensor data. This decentralized information fusion system will take advantage ofboth on-board tactical platform and off-board sensor data to generate a high performance identification capability. The algorithm development will address Automatic Target Recognition (ATR), ground target tracking, target cueing, and registration of imagery residing on both ground station (off-board) and tactical aircraft (on-board) systems. Analysis of data link and processing requirements/capabilities will be performed to determine an on-board and off-board fusion architecture.The off-board component would be targeted for ground station applications where multiple sources of information will come together. The off-board fusion algorithm employs a Bayesian approach to integrate information from multiple image sources such as SAR, EO, and FLIR as well as non-image based intelligence sources such as Ground Moving Target Indicators (GMTI). Model-based ATR technology will be an important module of this off-board fusion system for the extraction of target information from image data sources. Compression techniques and innovative representations of information will be investigated so that information can be transferred to the shooter platform using existing or planned communication channels. Finally, the tactical platform's on-board system will incorporate a fused feature methodology that utilizes off-board cues and on-board SAP. and FLIIR imagery for final on-board target identification. INTRODUCTIONThe SSIFRT project has very ambitious goals in terms ofboth image ATR and data fusion. The goals will be achieved by leveraging technology from a wide range of existing programs. The baseline SSIFRT program utilizes the off-board fusion system from the Information Fusion OnlOff-board Avionics (INFO) program, an AFRL Phase II SBIR, which has developed an all-source information fusion architecture for integrating information from multiple intelligence sources, including image data from SAR, FLIR, and potentially EO sources. Within this architecture, image data is preprocessed to