ABSTRACT
The research on recognition of radar intra-pulse modulated signals is an important development direction of radar countermeasure technology. In order to recognize the radar intra-pulse modulated signals effectively, many sgnal recognition techniques have been developed. In which, the one that based on residual convolutional neural network is one of the most promising techniques. In this paper, radar signal recognition techniques based on residual convolutional neural network are researched. The influence of model depth and residual block on time-frequency image recognition is verified. Firstly, using the feature extraction and recognition method of radar signal time-frequency image from Choi Williams, the problem of signal recognition is transformed into image recognition. Time-frequency images of 8 kinds of common radar signals are converted to grayscale images by the Choi Williams time-frequency transformation. Secondly, these grayscale images are recognized with six kinds of signal recognition algorithm models (AlexNet, DarkNet-19, GoogLeNet, VGG-16, ResNet-18, MobileNet-v2) and the recognition effect is compared. Thirdly, the residual block of the above six models are modified by increasing or decreasing residual and Inverted residual block, and the experimental results are compared. The results show that the shallow model AlexNet has the best accuracy and speed in recognizing time-frequency images, and the shallow network with an inverted residual block will improve the recognition speed with the cost of reducing the recognition accuracy slightly.
- Liu Gang. 2002. The basic theory of radar fingerprint analysis. Electronic countermeasure (6), 1-6.Google Scholar
- Zhang Gexiang. 2005. Research on intelligent recognition method of radar emitter signal. Doctoral thesis, Southwest Jiaotong University.Google Scholar
- Kawalec A and Owczarek R. 2004. Radar emitter recognition using intrapulse data//Proceedings of the 15th International Conference on Microwaves, Radar and Wireless Communications. Warsaw, Poland: IEEE: 435-438. DOI: 10.1109/MIKON.2004.1357059.Google ScholarCross Ref
- Gulum T O. 2007. Autonomous non-Linear classification of LPI radar siganl modulations. Monterey California Naval Postgraduate School, 2007,6(3):337-351.Google Scholar
- Pu Yunwei, Jin Weidong, Zhu Ming&Hu Laizhao. 2008. Feature extraction method of main ridge section of radar emitter signal ambiguity function. Journal of Infrared and Millimeter Wave (02), 133-137.Google Scholar
- Pu Yunwei, Jin Weidong&Hu Laizhao. 2009. Classification method of radar emitter signal instantaneous frequency derived features. Journal of Harbin Institute of Technology (01), 136-140.Google Scholar
- Pu Yunwei, Jin Weidong&Hu Laizhao. 2007. Emitter signal classification based on instantaneous frequency quadratic feature extraction. Journal of Southwest Jiaotong University (03), 373-379.Google Scholar
- Yun Lin,Xiao-Chun Xu & Zi-Cheng Wang. 2014. New Individual Identification Method of Radiation Source Signal Based on Entropy Feature and SVM. Journal of Harbin Institute of Technology (01),98-101.Google Scholar
- Zhang Ming , M. Diao , and L. Guo .2017. Convolutional Neural Networks for Automatic Cognitive Radio Waveform Recognition. IEEE Access PP.99(2017):1-1. DOI: 10.1109/ACCESS.2017.2716191.Google ScholarCross Ref
- Zhang Guozhu, Jiang Wenli, Monday Yu. 2004. Design of radiation source recognition system based on neural network. Systems Engineering and Electronic Technology (02), 268-272.Google Scholar
- Zhao Min. 2017. Classification and recognition of radar emitter signals under deep learning. Master's thesis, Xi'an University of Electronic Science and Technology.Google Scholar
- Zhang, Ming, Liu, Lutao, Diao, & Ming. 2016. LPI Radar Waveform Recognition Based on Time-Frequency Distribution. Sensors, Vol. 16, Pages 1682.Google Scholar
- Kong S H, Kim M, Hoang L M, Automatic LPI radar waveform recognition using CNN. IEEE Access, 2018, 6: 4207-4219. DOI: 10.1109/ACCESS.2017.2788942.Google ScholarCross Ref
- Li D J, Yang R, Li X, Radar signal modulation recognition based on deep joint learning. IEEE Access, 2020, 8: 48515-48528. DOI: 10.1109/ACCESS.2020.2978875.Google ScholarCross Ref
- Guo Q, Yu X, Ruan G. 2009. LPI radar waveform recognition based on deep convolutional neural network transfer learning. Symmetry, 2019, 11(4): 540.Google Scholar
- Lay B, Charlish A. 2020. Classifying LPI signals with transfer learning on CNN architectures. 2020 Sensor Signal Processing for Defence Conference (SSPD). IEEE, 2020: 1-5. DOI: 10.1109/SSPD47486.2020.9272032.Google ScholarCross Ref
- Lecun Y, Bengio Y, Hinton G. 2015. Deep learning. Nature, 2015, 521(7553):436-444.Google Scholar
- He K, Zhang X, Ren S, 2016. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.Google ScholarCross Ref
- Sandler M, Howard A, Zhu M, 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.Google ScholarCross Ref
Index Terms
- Research on Radar Signal Recognition Technology Based on Residual Convolutional Neural Network
Recommendations
An efficient deep convolutional neural network with features fusion for radar signal recognition
AbstractThis paper proposes an efficient deep convolutional neural network with features fusion for recognizing radar signal, which mainly includes data pre-processing, features extraction, multi-features fusion, and classification. Radar signals are ...
Research on the Modulation Recognition Method OFDM Signal Based on Short-time Fourier Transform and Convolutional Neural Network
ICBTA '21: Proceedings of the 2021 4th International Conference on Blockchain Technology and ApplicationsIn order to improve the modulation recognition accuracy of the Orthogonal Frequency Division Multiplexing (OFDM) signal under low signal-to-noise ratio, an OFDM signal modulation recognition method based on short-time Fourier transform and convolutional ...
Radar Target Recognition Based on Complex HRRP Using Convolutional Neural Network
SSPS '19: Proceedings of the 2019 International Symposium on Signal Processing SystemsOwing to the initial phase of the complex high resolution range profile (HRRP) is sensitive, real HRRP is usually used in the radar automatic target recognition (RATR) field, which partially causes losing information of the data. Based on this, this ...
Comments