US 5,210,798 AGranted

Vector neural network for low signal-to-noise ratio detection of a target

AssigneeLitton Systems, Inc.

InventorsLeon K. Ekchian, David D. Johnson, William F. Smith

Life of this patent

Estimating the term…

Loading patent…

Abstract

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.

Claims3

Dependent claims

A vector neural network (VNN) for the detection of a potential target where the energy of the target is insufficient in reference to a determinable signal-to-noise ratio (SNR) operating condition CHARACTERIZED IN THAT THE VNN comprises:

a) first means to establish operating control parameters for the VNN in response to the SNR where said control parameters include
(1) postulating a plurality of target tracks,
(2) propagating said tracks in a network of interconnected neurons,
(3) encoding said tracks to directional target energies,
b) second means to integrate target energies along at least one target track to develop a continuous target track over a function of both time and space,
c) third means to declare a target location by deferred thresholding of said integrated target energies relative to the SNR, and
d) fourth means to determine target direction by a backflow process with associated switching of said integrated target energies along said continuous target track.

4 more elements

Dependencies are inferred from the claim text.

Facts

Application: 07/667,633Filed 11 Mar 1991 · continuation in part
Priority: 19 Jul 1990
Granted: 11 May 1993
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

G06T 7/20
Image analysis: analysis of motion
G01S 7/417
Using analysis of echo signal for target characterisation; Target signature; Target cross-section: involving the use of neural networks
G01S 13/726
By using numerical data: multiple target tracking
G06N 3/04
Neural networks: architecture, e.g. interconnection topology