Radar high-resolution range profile target identification method based on width learning

Abstract

The invention discloses a radar high-resolution range profile target recognition method based on width learning. The method comprises the following steps: acquiring high-resolution range profile data and generating a training set; constructing a width learning model; training the width learning model by using the training set to obtain a trained width learning model; identifying original high-resolution range profile data to be identified by using the trained width learning model to obtain an identification result. According to the method, the high-dimensional features of the radar high-resolution range profile data are extracted by using the width learning model, and radar targets can be quickly identified on the premise of ensuring the identification precision, so that the method has obvious advantages in the aspects of prediction precision and identification time.

Description

technical field [0001] The invention belongs to the technical field of radar, and in particular relates to a radar high-resolution range image target recognition method based on width learning, which can be used to identify high-resolution range image targets. Background technique [0002] The echoes of broadband radar targets are called high-resolution range profiles. The high-resolution distance image is the projection distribution map of the sub-echoes of each scattering point of the target along the direction of the radar line of sight, which contains information such as the relative position and amplitude of the target scattering point, which has the advantages of easy acquisition and processing, and is very valuable for target classification and identification. Therefore, it has become a research hotspot in the field of radar automatic target recognition. [0003] At present, most of the literatures on radar automatic target recognition technology based on high-resolu...

AI Technical Summary

Problems solved by technology

However, as the amount of data increases, in order to achieve higher accuracy, most deep networks contain a large number of parameters and a large number of network layers, so a large number of computing resources and a long modeling cycle and recognition time are required.

In addition, since most deep networks use the backpropagation algorithm to minimize the error between the actual output of the network and the target output, and then update the weights layer by layer, the modeling speed of the deep network is also slowed down, which is very time-consuming

Images