Litton Systems, Inc.

William F Smith

Leon K Ekchian

David D Johnson

Fred W Erickson

The Radar Scan Converter System (1) receives range and azimuth data generated by a conventional radar as presented in a polar coordinate system, (2) stores this data in associated cell locations in a range/azimuth polar video map, and (3) displays this polar coordinate range/azimuth data in a Cartesian coordinate system, in real time, on a conventional computer monitor having a rectangular display formed by a relatively large number of pixels organized in the Cartesian coordinate system. Each pixel in the display is sequentially update by (1) selecting a respective pixel address, (2) determining the corresponding range/azimuth cell address in the polar video map, (3) reading the video level in this corresponding range/azimuth cell, and (4) in response to this associated video level, either initially loading or subsequently updating the selected pixel. The radar scan converter system displays (1) shades of gray or color, which may represent one or more video levels, and (2) has an image decay capability over repeated radar scans which is particularly suited for display of a moving target.

Radar scan converter system

A 'Barometer' Neuron enhances stability in a Neural Network System that, when used as a track-while-scan system, assigns sensor plots to predicted track positions in a plot/track association situation. The 'Barometer' Neuron functions as a bench-mark or reference system node that equates a superimposed plot and track to a zero distance as a 'perfect' pairing of plot and track which has a measured/desired level of inhibition. The 'Barometer' Neuron responds to the System inputs, compares these inputs against the level of inhibition of the 'perfect' pair, and generates a supplied excitation or inhibition output signal to the System which adjusts the System to a desired value at or near 1.0; this the reference level of inhibition of the 'perfect' pair.

'Barometer' neuron for a neural network

A vector neural network (VNN) of interconnected neurons is provided in transition mappings of potential targets wherein the threshold (energy) of a single frame does not provide adequate information (energy) to declare a target position. The VNN enhances the signal-to-noise ratio (SNR) by integrating target energy over multiple frames including the steps of postulating massive numbers of target tracks (the hypotheses), propagating these target tracks over multiple frames, and accommodating different velocity targets by pixel quantization. The VNN then defers thresholding to subsequent target stages when higher SNR's are prevalent so that the loss of target information is minimized, and the VNN can declare both target location and velocity. The VNN can further include target maneuver detection by a process of energy balancing hypotheses.

Vector neural networks

A vector neural network (VNN) of interconnected neurons is provided in transition mappings of potential targets wherein the threshold (energy) of a single frame does not provide adequate information (energy) to declare a target position. The VNN enhances the signal-to-noise ratio (SNR) by integrating target energy over multiple frames including the steps of postulating massive numbers of target tracks (the hypotheses), propagating these target tracks over multiple frames, and accommodating different velocity target by pixel quantization. The VNN then defers thresholding to subsequent target stages when higher SNR's are prevalent so that the loss of target information is minimized, and the VNN can declare both target location and velocity. The VNN can further include target maneuver detection by a process of energy balancing hypotheses.

Growing community of inventors

Los Angeles, CA, United States of America

William F Smith