A CNN-based HRRP target recognition method for a rejectable radar

Abstract

The invention relates to a CNN-based HRRP target recognition method for a rejectable radar, which comprises the following steps of: (1) acquiring HRRP time-frequency domain characteristic data of radar high-resolution range profile; (2) selecting training sample set and testing sample set; (3) constructing convolution neural network; (4) setting the adjustable cost function of convolution neural network; (5) training the convolution neural network; (6) obtaining the output results of the convolution neural network; 7) judging whether that reconstruction error is great than the threshold value,if so, rejecting the judgment of the target, otherwise, obtaining the recognition result. A multi-layer convolution neural network is introduced, high-dimensional features are extracted from radar HRRP data in time-frequency domain, which can effectively solve the problem that the accuracy of target recognition is not high due to the limited information of target features in the prior art, and has adjustable rejection ability to targets outside the database, and has better target recognition performance than the general methods.

Description

technical field [0001] The present invention belongs to the technical field of radar, and further relates to a method for recognizing radar high-resolution range profile HRRP (High-Resolution Range Profile) targets based on convolutional neural network CNN (Convolutional Neural Network) in the technical field of radar target recognition . The invention can reject and judge the target outside the radar database for the radar high-resolution range image data, and is used for the subsequent target recognition of the target in the database. Background technique [0002] Radar high-resolution range profile (HRRP) contains rich radar target structure features, and has the advantages of easy acquisition, storage and processing. It is very valuable for radar target recognition and classification, and has become a research hotspot in the field of radar automatic target recognition. Convolutional neural network (CNN) is a deep learning method, which avoids the complex feature extract...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that only a shallow neural network is used to analyze the time-domain information of radar HRRP data, and the method involved cannot fully utilize the time-frequency domain information of the data to extract high-dimensional features, which limits the use of The amount of feature information for target recognition

The disadvantage of this method is that it does not make full use of the extracted high-dimensional features to realize the rejection before target recognition, and it lacks the ability to reject when there are abnormal targets outside the library in the radar high-resolution range image sample. Effective rejection performance will reduce the accuracy of target recognition

Images