Coherent‐like integration for PD radar target detection based on short‐time Fourier transform

Zhang, Xiaowei; Zuo, Lei; Yang, Dongdong; Guo, Jianxin

doi:10.1049/iet-rsn.2019.0190

Cited by 14 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IAR-STFT combines the algorithms with time domain analysis and frequency domain analysis which not only reflects the frequency component, but also reflects the change rule of the frequency component changing with the delay of window. STFT [38], [39] of a signal x(t) is defined as…”

Section: Principle Of Iar-stftmentioning

confidence: 99%

A Weak Target Detection Algorithm IAR-STFT Based on Correlated K-distribution Sea Clutter Model

Liu¹,

Rao²,

Hu³

et al. 2023

RADIOENGINEERING

View full text Add to dashboard Cite

The detection performance of weak target on sea is affected by the special effects of sea clutter amplitude. Aiming at the time and space correlated of sea clutter, the correlated K-distribution sea clutter model is established by the sphere invariant random process algorithm. To solve the problems of range migration (RM) and Doppler frequency migration (DFM) of moving target in the case of long-time coherent accumulation, a novel integration detection algorithm, improved axis rotation short-time Fourier transform (IAR-STFT) is proposed in this paper, which is based on a generalization of traditional Fourier transform (FT) algorithm and combined with improved axis rotation. IAR-STFT not only can eliminate the RM effect by searching for the target motion parameters, but also can divide the non-stationary echo signal without range migration into several blocks. Each block of signal can be regarded as a stationary signal without DFM and FFT is performed on each signal separately. The signals of each block are accumulated to detect the target in the background of the above sea clutter. Finally, the effectiveness of the algorithm is verified by simulation. The results show that the detection ability of this algorithm is better than that of Radon-fractional Fourier transform, generalized Radon Fourier transform and Radon-Lv's distribution in low SNR environment, e.g., when the SNR is -45 dB, the detection ability of this algorithm is about 55%, which is higher than that of Radon-fractional Fourier transform, generalized Radon Fourier transform and Radon-Lv's distribution.

show abstract

Section: Principle Of Iar-stftmentioning

confidence: 99%

A Weak Target Detection Algorithm IAR-STFT Based on Correlated K-distribution Sea Clutter Model

Liu¹,

Rao²,

Hu³

et al. 2023

RADIOENGINEERING

View full text Add to dashboard Cite

show abstract

“…In view of this point, time-frequency analysis methods are employed to address the constraints of individual time-based or frequencybased feature extraction, which has become one of the most widely used feature extraction techniques. Techniques that include the Wigner-Ville distribution (WVD) [3], short-time Fourier transform (STFT) [4], and Choi-Williams distribution (CWD) [5] are commonly used to simultaneously characterize signals in the time-frequency domain. Qu et al [6] extracted the time-frequency images (TFIs) of the incoming signals using a multi-core Cohen-like time-frequency distribution.…”

Section: Introductionmentioning

confidence: 99%

Multilayer Decomposition Denoising Empowered CNN for Radar Signal Modulation Recognition

Jiang,

Zhou,

Shen

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Radar signal recognition plays a crucial role in modern electronic reconnaissance systems. With the increasing complexity of electromagnetic environments, radar signals are susceptible to noise interference under low signal-to-noise ratio (SNR) conditions, posing a challenge to accurate radar signal recognition. To address this issue, we propose a multilayer decomposition denoising empowered convolutional neural network (CNN) for radar signal recognition. Specifically, the original radar signals are first processed by multilayer decomposition denoising, which consists of variational mode decomposition (VMD), local mean decomposition (LMD), and wavelet thresholding (WT) in sequence, termed as VMD-LMD-WT. Then we use the Choi-Williams distribution (CWD) to convert the denoised signals into time-frequency images (TFIs). Finally, an improved CNN with dilated convolution is employed for radar signal recognition. Experiments demonstrate that the multilayer decomposition denoising method effectively improves the SNR of the original signal, which is beneficial for the subsequent recognition task. The recognition accuracy is improved by about 11% compared to that directly using the original signal. Furthermore, compared to the current network models, the proposed CNN network can efficiently extract the signal features and improve the detection accuracy of low probability of intercept (LPI) radar signals.The recognition accuracy reaches 75.3% for 12 signals when the SNR is low to −14dB.INDEX TERMS LPI radar signal recognition, signal denoising, time-frequency analysis, convolutional neural network.

show abstract

“…This urgently requires the development of a high-performance method to automatically recognize LPI waveform signals. Numerous existing waveform recognition approaches have exploited several principal time-frequency analysis (TFA) techniques [2], such as short-time Fourier transforms, Wigner-Ville distribution (WVD), and Choi-William distribution (CWD), to extract the radio characteristics in the time and frequency domains [3], [4]. However, the traditional machine learning algorithms adopted by conventional approaches cannot learn high-level representational features in time-frequency image (TFI) to discriminate many waveforms explicitly [5].…”

Section: Introductionmentioning

confidence: 99%

Densely-Accumulated Convolutional Network for Accurate LPI Radar Waveform Recognition

Huynh‐The

Pham

Nguyen

et al. 2021

2021 IEEE Global Communications Conference (GLOBECOM)

View full text Add to dashboard Cite

This paper presents a deep learning-based method to automatically recognize low probability of intercept (LPI) radar waveforms against diversified jamming attacks. Concretely, an efficient convolutional neural network (CNN) architecture, namely Densely-Accumulated Network (DANet), is introduced to learn the time-frequency representation transformed by the Wigner-Ville distribution. Such an architecture has several novel densely-accumulated connection modules specified by various symmetric and asymmetric convolutional layers to enrich diversified features at multiple representational maps. Besides, the skip-connection and dense-connection are leveraged to improve feature learning efficiency and prevent the vanishing gradient when the network goes deeper. Some image processing techniques (e.g., global thresholding and digital filtering) are adopted to enhance the quality of time-frequency image. Relying on simulations, we benchmark the proposed method on a synthetic 13-waveform dataset and also investigate the influence of hyperparameters (such as image size, number of modules, training data size) on the overall recognition performance. Remarkably, with average accuracy of 98.2% at 0 dB signal-to-noise ratio (SNR), DANet outperforms several backbone CNNs and state-ofthe-art networks of LPI waveform recognition while keeping a cost-efficient model.

show abstract

Coherent‐like integration for PD radar target detection based on short‐time Fourier transform

Cited by 14 publications

References 25 publications

A Weak Target Detection Algorithm IAR-STFT Based on Correlated K-distribution Sea Clutter Model

A Weak Target Detection Algorithm IAR-STFT Based on Correlated K-distribution Sea Clutter Model

Multilayer Decomposition Denoising Empowered CNN for Radar Signal Modulation Recognition

Densely-Accumulated Convolutional Network for Accurate LPI Radar Waveform Recognition

Contact Info

Product

Resources

About