AUTOMATIC RECOGNITION

A NEED EXISTS FOR THE DEVELOPMENT OF AN ARTIFICIAL INTELLIGENCE (AI)-BASED COMPUTER PROGRAM (ALGORITHM) WITH A HEURISTIC DATA BASE, OPERATIVE ON A MILITARIZED 16-BIT MICROPROCESSOR, SUCH AS, INTEL 8086 WHICH WOULD BE RESIDENT ON A COMBAT VEHICLE, FOR THE AUTOMATIC RECOGNITION OF MILITARY TARGETS. TARGET IDENTIFICATION WHICH INVOLVESCOMPLEX HUMAN DECISION MAKING IS NOT VERY RELIABLE WHEN SUCH DECISION IS MADE UNDER THE STRESS OF COMBAT ENGAGEMENT, EVEN THOUGH A DISTINCT AND UNAMBIGUOUS TARGET IMAGE MIGHT BE AVAILABLE. VISUAL OR IR IMAGE-BASED TARGET IDENTIFICATION IS HARDER, AND HENCE, LESS RELIABLE WHEN THE TARGETS ARE PARTIALLY OR WHOLLY OBSCURED BY CLOUDS WHICH DIMINISH TARGET CONTRAST WITH THE BACKGROUND OR BY BATTLEFIELD SMOKE OR DUST WHICH BLUR TARGET DEFINITIONS. THE PROPOSED RESEARCH WILL ADDRESS SEVERAL KEY ELEMENTS IN THE BATTLEFIELD DATA INTERPRETATION PROBLEM AND WILL INCLUDE AI DECISION TOOLS, SUCH AS, PERCEPTUAL REASONING TECHNIQUES AND EXPERT-RULE-BASED (ERB) SYSTEMS, SENSOR MODELING, HEURISTIC DATA BASE CREATION, AND SENSOR UTILIZATION STRATEGIES. THE RESEARCH WILL RESULT IN INTEGRATION, CORRELATION AND OPTIMIZATION ALGORITHMS FOR THE MULTIPLE SENSOR SYSTEM AND AN EVALUATION OF APPROPRIATE INFORMATION PROCESSING TECHNIQUES ALL IN THE CONTEXT OF CREATING AN AI-BASED AUTOMATIC TARGET RECOGNITION (ATR) PROGRAM.