Radar target identification method on basis of biomimetic pattern identification theory

Abstract

The invention discloses a radar target identification method on the basis of the biomimetic pattern identification theory, which includes steps of calculating echo data corresponding to a radar target by the physical optic method, analyzing the radar echo data and building one-dimension range profile of the radar target, preprocessing the one-dimension range profile of the radar target into characteristic vectors, and then identifying different targets by the biomimetic pattern identification theory. As a new pattern identification method, the radar target identification method on the basis of the biomimetic pattern identification theory is characterized by being based on 'understanding' rather than 'dividing'. Particularly, the targets are 'understood' by covering feature samples of each type of targets in high-dimensional space by the aid of a hyper-sausage model, so that correct recognition rate is increased effectively, while defects that conventional radar target identification methods are poor in identification capacity and original data are required to be retrained once a new type targets are added are avoided.

Description

technical field [0001] The invention belongs to the technical field of radar target recognition, in particular to a radar target recognition method based on bionic pattern recognition theory. Background technique [0002] The process of radar target recognition technology is generally to extract the relevant information signs and stable features of the target from the echo of the radar target, construct the feature template library of the known target, then use the template library to train the classifier, and finally use the trained classifier to identify objects. Under the illumination of high-resolution radar, the echo of the target occupies multiple range image units in the distance direction, showing continuous fluctuation characteristics, which is usually called the high-resolution one-dimensional range image of the target, and the high-resolution one-dimensional range image of the radar target It can provide the geometric structure information of the target along the...

AI Technical Summary

Problems solved by technology

These partition-based pattern recognition methods often have several problems: (1) If a linear function (hyperplane) is used as the classification surface, it cannot be well adapted to the complex distribution of the sample space, which will lead to a high false recognition rate

(2) These partition-based pattern recognition methods divide the entire sample space into corresponding subspaces according to the target number of known samples. For samples of new targets that are not in the target template library, they will be mistakenly identified as certain subspaces in the target template library. A class of targets, resulting in a high misrecognition rate of this method, and does not have the ability to reject recognition

(3) If you want to add samples of new targets to the template library, you need to re-divide the sample space composed of samples in the entire template library, which is time-consuming and laborious

Improving the linear function to a nonlinear function, such as using the Gaussian kernel function in the support vector machine, can solve the problem (1), but this has not solved the second and third problems

Images