A proposed system for a visual tracker is presented that relies on information developed from previous tracking scenarios stored in a knowledge base to enhance tracking performance. The system is comprised of a centroid tracker front end that supplies segmented image features to a data reduction algorithm and subsequently to a track processor operating under one of two modes, learn or track. While in learn mode, a human operator provides identification cues for membership in a long-term storage relation within a knowledge base. In track mode the system operates autonomously with a cognitive processing algorithm replacing the human operator. The autonomous system functions as a correlation tracker by comparing processed input to data that was stored in the knowledge base during learn mode. Results determined from the classification generate tracker directives that either enhance the current track or cause the tracker to search for alternate targets based on a global target tracking list.

Object identification and tracking applications of pattern recognition at video rates is a problem of wide interest, with previous attempts limited to very simple threshold or correlation (restricted window) methods. New high-speed algorithms together with fast digital hardware have produced a system for missile and aircraft identification and tracking that possesses a degree of ``intelligence'' not previously implemented in a real-time tracking system. Adaptive statistical clustering and projection-based classification algorithms are applied in real time to identify and track objects that change in appearance through complex and nonstationary background/foreground situations. Fast estimation and prediction algorithms combine linear and quadratic estimators to provide speed and sensitivity. Weights are determined to provide a measure of confidence in the data and resulting decisions. Strategies based on maximizing the probability of maintaining track are developed. This paper emphasizes the theoretical aspects of the system and discusses the techniques used to achieve real-time implementation.

This paper presents a structure for digital processing and characterization of video signals using the theory of projections. A new theorem giving necessary and sufficient conditions for unique representation of a video signal with two orthogonal projections is presented. Algorithms are given for on-line application of the uniqueness conditions. A microprogrammable processor is presented for computing the projections and characterizing the structural properties of an image in real-time.