Abstract
Deep neural networks are used as effective methods for the Low Probability of Intercept (LPI) radar waveform recognition. However, existing models’ performance degrades seriously at low Signal-to-Noise Ratios (SNRs) because the effective features extracted by the networks are insufficient under noise jamming. In this paper, we propose a multi-resolution deep feature fusion method for LPI radar waveform recognition. First, we apply the enhanced Fourier-based Synchrosqueezing Transform (FSST), which shows good performance at low SNRs, to convert radar signals into time-frequency images. Then, we construct a multi-resolution deep convolutional network to extract more deep features from each resolution channel. Next, we explore an interactive feature fusion strategy for deep feature fusion. By some down-sampling or up-sampling blocks, different resolution features are fused to generate new features. Finally, we apply a fusion algorithm to the fully connected layer to achieve classification fusion for better performance. Simulation experiments on twelve kinds of LPI radar waveforms show that the overall recognition accuracy of our method can reach 95.2% at the SNR of −8 dB. It is proved that our approach does indeed improve the recognition accuracy effectively at low SNRs.
Highlights
Low Probability of Intercept (LPI) radar, not intercepted by non-cooperative receivers, has been widely used in modern radar systems
We propose a multi-resolution deep feature fusion method for LPI radar waveform recognition, to address the problem of insufficient features extracted from deep learning networks under noise jamming
When the Signal-toNoise Ratios (SNRs) is -8 dB, our method can still achieve 95.2% recognition accuracy, which exceeds Choi-William Distribution (CWD)-MFCNN by 2.4% and Fourier-based Synchrosqueezing Transform (FSST)-Convolutional Neural Network (CNN) by 11.3%
Summary
LPI radar, not intercepted by non-cooperative receivers, has been widely used in modern radar systems. The features extracted from single-resolution inputs are insufficient to distinguish various radar signals at low SNRs, especially similar signals, making it difficult to improve recognition performance. Considering that the features at different resolutions have different contributions to the recognition performance, we will try to use T-F images with multiple resolutions for network training and improve the fusion strategy to extract deep features. We propose a multi-resolution deep feature fusion method for LPI radar waveform recognition, to address the problem of insufficient features extracted from deep learning networks under noise jamming. 4) Use a fusion algorithm to the Fully Connected (FC) layer with different resolutions to achieve classification fusion, and select the Error-Correcting Output Coding-Support Vector Machine (ECOC-SVM) as a classifier, which can improve the fault tolerance of the classification It shows a significant improvement in recognition accuracy.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
