LPI Radar Waveform Recognition Based on Features from Multiple Images

Abstract

Detecting and classifying the modulation type of the intercepted noisy LPI (low probability of intercept) radar signals in real-time is a necessary survival technique in the electronic intelligence systems. Most radar signals have been designed to have LPI properties; therefore, the LPI radar waveform recognition technique (LWRT) has recently gained increasing attention. In this paper, we propose a multiple feature images joint decision (MFIJD) model with two different feature extraction structures that fully extract the pixel feature to obtain the pre-classification results of each feature image for the non-stationary characteristics of most LPI radar signals. The core technology of this model is combining the short-time autocorrelation feature image, double short-time autocorrelation feature image and the original signal time-frequency image (TFI) simultaneously input into the hybrid model classifier, which is suitable for non-stationary signals, and it has higher universality. We demonstrate the performance of MFIJD by simulating 11 types of the signals defined in this paper and generating training sets and test sets. The comparison with the literature shows that the proposed methods not only has a high universality for LPI radar signals, but also better adapts to LPI radar waveform recognition at low SNR (signal to noise ratio) environment. The overall recognition rate of the method reaches 87.7% when the SNR is −6 dB.Sensors 2020, 20, 526 2 of 23 some existing feature extraction methods are highly targeted, mainly for some specific radar emitter signals. For another thing, these methods rarely involve problems with noise effects and low SNR. In fact, radar signals, especially LPI radar signals, are inevitably subject to large amounts of noise during propagation and reception [5], and LPI radars usually have lower power and it is difficult to directly classify [6]. In current research, there have been some LPI waveform recognition technologies (LWRT), which use feature extraction and classification techniques. Time-frequency analysis (TFA) is widely used in the feature extraction since LPI radar signals are usually non-stationary signals, such as Smoothed Pseudo-Wigner Distribution (SPWD) [7], Wigner Ville Distribution (WVD) [8], Short-Time Fourier Transform (STFT) [9][10][11], and Choi-Williams Distribution (CWD) [6,[12][13][14][15][16]. Combined with deep learning in the field of computer vision [17] and models of neural network structures, researchers have obtained better recognition results from the time-frequency feature of signals [18]. The radar signal is first time-frequency transformed into a two-dimensional time-frequency image (TFI), which then is preprocessed and sent to a neural network for training. In the area of classifier design, classification methods include multi-Layer Perceptron (MLP) [11], conditional decision for different features [11,15], Convolutional Neural Networks (CNN) [14], Elman Neural Networks (ENN) [6], and support vector machines (SVM) [6,16]. In addition, there have been hy...

LPI Radar Waveform Recognition Based on Neural Architecture Search

“…Previous research [ 18 ] found that, even if the network performance is good enough (it means that the network's recognition accuracy rate of the trained dataset had reached to a high level and the recognition accuracy rate to most of the waveforms can reach 99%), there are still some signals that are easily confused. The similarity between the waveforms is high (or the similarity between the converted time-frequency images is high) and the difference of the extracted features is not obvious.…”

Deep-Learning for Radar: A Survey

“…In [31], a 7-layer CNN along with a novel tree structure-based process optimization tool (TPOT) classifier was designed. In [32], Ma et al employed two different DNN structures to approach the waveform classification problem: a 11-layer CNN and a bidirectional LSTM, with the former exhibiting better performance. In [33], transfer learning was employed to counter the problem of limited training data.…”

Estimating the Instantaneous Frequency of Linear and Nonlinear Frequency Modulated Radar Signals—A Comparative Study

“…The most common classifiers in radar AMC algorithms are hierarchical decision trees and artificial neural networks, whereas there are a lot of possible signal features, including those derived from instantaneous signal properties [ 4 , 5 , 6 ], higher-order statistics [ 6 , 7 , 8 ], time-frequency distributions (TFDs) [ 8 , 9 , 10 ] or power spectral density [ 11 , 12 ]. Over the recent years, one can notice an increasing number of deep learning AMC algorithms, especially those using time-frequency image features combined with a convolutional neural network classifier [ 13 , 14 , 15 ].…”