Target identification method based on linear frequency modulation wavelet atomic network

Abstract

The invention provides a target identification method based on a linear frequency modulation wavelet atomic network. The target identification method comprises the steps of S1, offline training the linear frequency modulation wavelet atomic network; and S2, classifying the targets by using the linear frequency modulation wavelet atomic network obtained in the step S1, and outputting a recognitionresult. Based on a three-layer feedforward neural network structure, linear frequency modulation wavelet atoms are used as a characteristic extraction primary function of an input layer, the input layer realizes characteristic extraction through linear frequency modulation wavelet atom transformation, and a neural network classifier is formed by a hidden layer and an output layer. Compared with the prior art, the utility model has the following advantages: 1, richer feature information of a target can be obtained through linear frequency modulation wavelet atom transformation, better effectivedata support is provided for a classifier, and the accuracy of target identification is improved; 2, through combination of feature extraction and classification, parameter adjustment can be carriedout in real time according to different target features and recognition environments, and the recognition performance and the anti-noise performance of the recognition system are improved;

Description

technical field [0001] This creation involves the fields of signal processing and pattern recognition, especially a target recognition method based on LFM wavelet atomic network. Background technique [0002] With the rapid development of modern signal processing technology and the urgent needs of practical applications, automatic target recognition technology is playing an increasingly important role in modern high-tech warfare. At present, the recognition technology based on electromagnetic scattering images has been widely used in the recognition of various targets in the sea, land and air, and is one of the research hotspots in the field of target recognition. [0003] Automatic target recognition systems generally include two independent stages of feature extraction and classification decision-making. For the feature extraction method, Guo Zunhua, Li Da, and Zhang Boyan mentioned in the article "Radar High-range Resolution One-Dimensional Image Target Recognition" on p...

AI Technical Summary

Problems solved by technology

[0005] In addition, in the prior art, there is also the following second defect: For targets with complex scattering characteristics, the phenomenon of scattering point occlusion and moving scattering points on the target will cause certain damage to the stable scattering model, and the traditional method is difficult to Realize the extraction of effective features of this type of target; for target recognition in complex environmental backgrounds, it is also necessary to consider how to ensure the accuracy of recognition as much as possible under noise conditions, that is, how to obtain feature information that contains more abundant targets and reflects the nature of the target, Improving the anti-noise performance of the recognition system

[0011] However, this will lead to new problems: the richer the extracted feature information, the greater the challenge for the recognition system to classify these features, and how to choose a suitable classifier becomes the key to the success of recognition

Images