A Robust Recognition Method for One-Dimensional Range Profiles Based on Euler Kernel Principal Component Analysis

Abstract

The invention discloses a one-dimensional distance image robust identification method based on Euler kernel principal component analysis. Firstly, the normalized spectrum amplitude feature is extracted from the measured one-dimensional range image signal sample; then, the Euler kernel function is used to map it to the kernel space, the kernel matrix is ​​calculated, and the principal component feature projection is obtained by principal component analysis (PCA) Matrix to obtain the principal components of the kernel space features of the sample; finally, use the support vector machine classifier (SVM) for feature recognition. Based on the Euler kernel function, the present invention realizes the same-dimensional kernel space mapping, not only enhances the linear separability of one-dimensional range image data, but does not increase the space dimension, and reduces the amount of calculation. Using the principal component analysis method to extract the principal components of its nuclear space features further reduces the feature dimension and weakens the influence of noise, so that the method can process large data signals faster, and can maintain high recognition accuracy in noisy environments. Compared with the traditional kernel principal component analysis method, it has obvious advantages.

Description

technical field [0001] The invention relates to a method for identifying a radar one-dimensional signal, in particular to a technology for quickly and accurately identifying a radar one-dimensional range image in an interference environment. Background technique [0002] Radar target recognition is an important research direction of radar signal processing. Radar high-resolution one-dimensional range profile (HRRP) reflects the distribution of target scattering points along the radar line-of-sight direction, which contains rich target structural features, and its inherent advantages are easy acquisition and small data volume. Therefore, target recognition based on HRRP has always been a research hotspot in the field of radar target recognition. Since the linear inseparability of large-angle HRRP data itself is more and more serious in the noise interference environment, some traditional classification and identification schemes such as the maximum correlation criterion clas...

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: Aiming at the above-mentioned prior art, a robust recognition method for one-dimensional range images based on Euler kernel principal component analysis is proposed, which can obtain satisfactory recognition accuracy at a relatively small calculation cost in a noisy environment. When the classifier is fixed, the recognition accuracy can be increased by 3-4 percentage points compared with the traditional kernel principal component analysis method

Images