High-Resolution Radar Target Recognition via Inception-Based VGG (IVGG) Networks

Wang, Wei; Zhang, Chengwen; Tian, Jinge; Wang, Xin; Ou, Jianping; Zhang, Jun; Ji, Li

doi:10.1155/2020/8893419

Cited by 17 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The generated signal is transformed by CWD to obtain TFI. Unlike SAR images [ 20 ] in radar target recognition and high-resolution radar target images [ 21 ], TFI is a digital image with low image information loss, which is convenient for computer processing and analysis.…”

Section: Resultsmentioning

confidence: 99%

A Radar Signal Recognition Approach via IIF-Net Deep Learning Models

Zhang

et al. 2020

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

In the increasingly complex electromagnetic environment of modern battlefields, how to quickly and accurately identify radar signals is a hotspot in the field of electronic countermeasures. In this paper, USRP N210, USRP-LW N210, and other general software radio peripherals are used to simulate the transmitting and receiving process of radar signals, and a total of 8 radar signals, namely, Barker, Frank, chaotic, P1, P2, P3, P4, and OFDM, are produced. The signal obtains time-frequency images (TFIs) through the Choi–Williams distribution function (CWD). According to the characteristics of the radar signal TFI, a global feature balance extraction module (GFBE) is designed. Then, a new IIF-Net convolutional neural network with fewer network parameters and less computation cost has been proposed. The signal-to-noise ratio (SNR) range is −10 to 6 dB in the experiments. The experiments show that when the SNR is higher than −2 dB, the signal recognition rate of IIF-Net is as high as 99.74%, and the signal recognition accuracy is still 92.36% when the SNR is −10 dB. Compared with other methods, IIF-Net has higher recognition rate and better robustness under low SNR.

show abstract

Section: Resultsmentioning

confidence: 99%

A Radar Signal Recognition Approach via IIF-Net Deep Learning Models

Zhang

et al. 2020

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning method has been widely used in target recognition [30]. Wang et al studied the recognition of SAR and radar signals by using deep learning method [31,32]. We can also use the deep learning method to identify the types of radar jamming signals and take corresponding anti-jamming measures in future research.…”

Section: Resultsmentioning

confidence: 99%

A Novel Radar Waveform Design for Anti-Interrupted Sampling Repeater Jamming via Time-Frequency Random Coded Method

Ji¹,

Luo²,

Duan³

et al. 2020

PIER M

Self Cite

View full text Add to dashboard Cite

According to the orthogonality of each sub-carrier in the multi-carrier phase-coded (MCPC) signal, this paper focuses on anti-interrupted sampling repeater jamming (ISRJ) and creatively proposes a novel radar signal based on time-frequency random coded (TFRC) method, namely TFRC-MCPC signal. Based on the perspective of waveform design, the TFRC-MCPC signal adopts a chaotic sequence with good pseudo-random to code each chip in time-domain and each subcarrier in frequencydomain. The TFRC method increases the pseudo-randomness of radar waveform pulses and reduces the correlation between radar echo and ISRJ, thereby effectively suppressing the interference of false targets. The TFRC-MCPC method and common filter design methods do not conflict with each other and can be used in combination. The simulation experiment results show that under the typical parameters described in the paper, compared with the traditional MCPC signal and LFM signal, the signaljamming ratio (SJR) improvement factor of the TFRC-MCPC signal is optimized by 1-2 dB after pulse compression, which verifies its feasibility and effectiveness.

show abstract

“…Meanwhile, some deep learning methods combined with traditional methods have achieved good results in target recognition and classification [ 30 ]. On the other hand, designing specific deep learning networks based on the characteristics of classification targets is a very effective classification approach [ 31 , 32 ]. Therefore, how to give full use of the advantages of different methods is also worth further studying.…”

Section: Discussionmentioning

confidence: 99%

A New Image Classification Approach via Improved MobileNet Models with Local Receptive Field Expansion in Shallow Layers

Wang

Zou

et al. 2020

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

Because deep neural networks (DNNs) are both memory-intensive and computation-intensive, they are difficult to apply to embedded systems with limited hardware resources. Therefore, DNN models need to be compressed and accelerated. By applying depthwise separable convolutions, MobileNet can decrease the number of parameters and computational complexity with less loss of classification precision. Based on MobileNet, 3 improved MobileNet models with local receptive field expansion in shallow layers, also called Dilated-MobileNet (Dilated Convolution MobileNet) models, are proposed, in which dilated convolutions are introduced into a specific convolutional layer of the MobileNet model. Without increasing the number of parameters, dilated convolutions are used to increase the receptive field of the convolution filters to obtain better classification accuracy. The experiments were performed on the Caltech-101, Caltech-256, and Tubingen animals with attribute datasets, respectively. The results show that Dilated-MobileNets can obtain up to 2% higher classification accuracy than MobileNet.

show abstract

High-Resolution Radar Target Recognition via Inception-Based VGG (IVGG) Networks

Cited by 17 publications

References 19 publications

A Radar Signal Recognition Approach via IIF-Net Deep Learning Models

A Radar Signal Recognition Approach via IIF-Net Deep Learning Models

A Novel Radar Waveform Design for Anti-Interrupted Sampling Repeater Jamming via Time-Frequency Random Coded Method

A New Image Classification Approach via Improved MobileNet Models with Local Receptive Field Expansion in Shallow Layers

Contact Info

Product

Resources

About