Discussion on “Improved radar visibility of small targets in sea clutter”

1966 ◽  
Vol 32 (3) ◽  
pp. 147
Author(s):  
D.C. Cooper ◽  
J. Croney ◽  
R. Voles ◽  
J. Rowe ◽  
G.A. Egler ◽  
...  
Keyword(s):  
2021 ◽  
Vol 9 (6) ◽  
pp. 651
Author(s):  
Yan Yan ◽  
Hongyan Xing

In order for the detection ability of floating small targets in sea clutter to be improved, on the basis of the complete ensemble empirical mode decomposition (CEEMD) algorithm, the high-frequency parts and low-frequency parts are determined by the energy proportion of the intrinsic mode function (IMF); the high-frequency part is denoised by wavelet packet transform (WPT), whereas the denoised high-frequency IMFs and low-frequency IMFs reconstruct the pure sea clutter signal together. According to the chaotic characteristics of sea clutter, we proposed an adaptive training timesteps strategy. The training timesteps of network were determined by the width of embedded window, and the chaotic long short-term memory network detection was designed. The sea clutter signals after denoising were predicted by chaotic long short-term memory (LSTM) network, and small target signals were detected from the prediction errors. The experimental results showed that the CEEMD-WPT algorithm was consistent with the target distribution characteristics of sea clutter, and the denoising performance was improved by 33.6% on average. The proposed chaotic long- and short-term memory network, which determines the training step length according to the width of embedded window, is a new detection method that can accurately detect small targets submerged in the background of sea clutter.


1975 ◽  
Vol 45 (3) ◽  
pp. 105 ◽  
Author(s):  
J. Croney ◽  
A. Woroncow ◽  
B.R. Gladman
Keyword(s):  

Author(s):  
Rujiang Guo ◽  
Ming Hao ◽  
Ming Li ◽  
Yinghong Ni ◽  
Zhenbang Cheng

2015 ◽  
Vol 32 (2) ◽  
pp. 310-317 ◽  
Author(s):  
Yan Jin ◽  
Zezong Chen ◽  
Lingang Fan ◽  
Chen Zhao

AbstractA new method is proposed to detect small targets embedded in sea clutter for land-based microwave coherent radar using spectral kurtosis as a signature from radar data. It is executed according to the following procedures. First, the echoes of radar from each range gate are processed by the technique of short-time Fourier transform. Then, the kurtosis of each Doppler channel is estimated from the time–Doppler spectra. Last, the spectral kurtosis is compared to a threshold to determine whether a target exists. The proposed method is applied to measured datasets of different sea conditions from slight to moderate. The signal from a small boat is detected successfully. Furthermore, the detection performance of the proposed method is analyzed by the way of Monte Carlo simulation. It demonstrates that the spectral kurtosis–based detector works well for weak target detection when the target’s Doppler frequency is beyond the strong clutter region.


Sign in / Sign up

Export Citation Format

Share Document