Track assembly from two-dimensional image of binary data

An automatic method for track assembly is presented which can initiate new tracks, assign new measurements to the appropriate track, and eliminate false tracks due to clutter. Consecutive frames of binary images are combined and then screened using a three-by-three window. Successive levels of data processing reduce the noise still further, and in a cluttered environment (noise in 5% of the pixels), it may be necessary to use three or more levels to eliminate false tracks due to noise. Curved paths and crossing tracks are handled without difficulty, and track-like noise can be eliminated by preprocessing. A special coding scheme has been implemented on an array processor to obtain a processing rate of 160,000 pixels per second, independent of the number of targets. Theoretical calculations are developed for the probability of false tracks along with verifying experimental results.