Full Text:   <5356>

Summary:  <1532>

CLC number: TN957.51

On-line Access: 2024-08-27

Received: 2023-10-17

Revision Accepted: 2024-05-08

Crosschecked: 2020-05-18

Cited: 0

Clicked: 6626

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Guan-qing Li

https://orcid.org/0000-0002-9789-8931

Zhi-yong Song

https://orcid.org/0000-0002-3833-0510

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2020 Vol.21 No.10 P.1504-1520

http://doi.org/10.1631/FITEE.1900523


A convolutional neural network based approach to sea clutter suppression for small boat detection


Author(s):  Guan-qing Li, Zhi-yong Song, Qiang Fu

Affiliation(s):  National Key Laboratory of Science and Technology on ATR, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China

Corresponding email(s):   liguanqing09@nudt.edu.cn, songzhiyong08@nudt.edu.cn

Key Words:  Convolutional neural networks, Class activation map, Short-time Fourier transform, Small target detection, Sea clutter suppression


Guan-qing Li, Zhi-yong Song, Qiang Fu. A convolutional neural network based approach to sea clutter suppression for small boat detection[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(10): 1504-1520.

@article{title="A convolutional neural network based approach to sea clutter suppression for small boat detection",
author="Guan-qing Li, Zhi-yong Song, Qiang Fu",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="21",
number="10",
pages="1504-1520",
year="2020",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1900523"
}

%0 Journal Article
%T A convolutional neural network based approach to sea clutter suppression for small boat detection
%A Guan-qing Li
%A Zhi-yong Song
%A Qiang Fu
%J Frontiers of Information Technology & Electronic Engineering
%V 21
%N 10
%P 1504-1520
%@ 2095-9184
%D 2020
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1900523

TY - JOUR
T1 - A convolutional neural network based approach to sea clutter suppression for small boat detection
A1 - Guan-qing Li
A1 - Zhi-yong Song
A1 - Qiang Fu
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 21
IS - 10
SP - 1504
EP - 1520
%@ 2095-9184
Y1 - 2020
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1900523


Abstract: 
Current methods for radar target detection usually work on the basis of high signal-to-clutter ratios. In this paper we propose a novel convolutional neural network based dual-activated clutter suppression algorithm, to solve the problem caused by low signal-to-clutter ratios in actual situations on the sea surface. Dual activation has two steps. First, we multiply the activated weights of the last dense layer with the activated feature maps from the upsample layer. Through this, we can obtain the class activation maps (CAMs), which correspond to the positive region of the sea clutter. Second, we obtain the suppression coefficients by mapping the CAM inversely to the sea clutter spectrum. Then, we obtain the activated range-Doppler maps by multiplying the coefficients with the raw range-Doppler maps. In addition, we propose a sampling-based data augmentation method and an effective multiclass coding method to improve the prediction accuracy. Measurement on real datasets verified the effectiveness of the proposed method.

一种用于小船检测的基于卷积神经网络的海杂波抑制方法

李官清,宋志勇,付强
国防科技大学电子科学学院ATR国防科技重点实验室,中国长沙市,410073

摘要:目前的雷达目标检测方法通常基于高信杂比。本文提出一种新的基于卷积神经网络的双激活杂波抑制算法,以解决实际海况中低信杂比下的小目标检测问题。双激活有两个步骤。首先,激活最后一个全连接层的权重和来自上采样层的特征图获得类激活图,对应于海杂波的轮廓;其次,将类激活图反向映射到海杂波频谱得到抑制系数。抑制系数与原始距离多普勒图相乘即得到杂波抑制后的距离多普勒图。此外,提出一种基于采样的数据增强方法和一种有效的多类编码方法以提高预测精度。实测数据验证了方法的有效性。

关键词:卷积神经网络;类激活图;短时傅立叶变换;小目标检测;海杂波抑制

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Adolfsson L, Rahm M, 2018. Machine Learning for Categorization of Small Boats and Sea Clutter. MS Thesis, Chalmers University of Technology, Göteborg, Sweden.

[2]Angelov A, Robertson A, Murray-Smith R, et al., 2018. Practical classification of different moving targets using automotive radar and deep neural networks. IET Radar Sonar Navig, 12(10):1082-1089.

[3]Conte E, de Maio A, 2004. Mitigation techniques for non-Gaussian sea clutter. IEEE J Ocean Eng, 29(2):284- 302.

[4]Cui XD, Goel V, Kingsbury B, 2015. Data augmentation for deep neural network acoustic modeling. IEEE/ACM Trans Audio Speech Lang Process, 23(9):1469-1477.

[5]Del-Rey-Maestre N, Jarabo-Amores MP, Mata-Moya D, 2018. Machine learning techniques for coherent CFAR detection based on statistical modeling of UHF passive ground clutter. IEEE J Sel Top Signal Process, 12(1):104-118.

[6]de Maio A, Foglia G, Conte E, 2005. CFAR behavior of adaptive detectors: an experimental analysis. IEEE Trans Aerosp Electron Syst, 41(1):233-251.

[7]Dong Y, 2012. Optimal coherent radar detection in a K-distributed clutter environment. IET Radar Sonar Navig, 6(5):283-292.

[8]Farina A, Gini F, Greco MV, et al., 1997. High resolution sea clutter data: statistical analysis of recorded live data. IEE Proc Radar Sonar Navig, 144(3):121-130.

[9]Fernández JRM, Vidal JDLCB, 2018. Fast selection of the sea clutter preferential distribution with neural networks. Eng Appl Artif Intell, 70:123-129.

[10]Gilbert AC, Indyk P, Iwen M, et al., 2014. Recent developments in the sparse Fourier transform: a compressed Fourier transform for big data. IEEE Signal Process Mag, 31(5):91-100.

[11]Gini F, Greco MV, Diani M, et al., 2000. Performance analysis of two adaptive radar detectors against non-Gaussian real sea clutter data. IEEE Trans Aerosp Electron Syst, 36(4):1429-1439.

[12]Gini F, Farina A, Montanari M, 2002. Vector subspace detection in compound-Gaussian clutter. Part II: performance analysis. IEEE Trans Aerosp Electron Syst, 38(4):1312-1323.

[13]Greco M, Gini F, Rangaswamy M, 2006. Statistical analysis of measured polarimetric clutter data at different range resolutions. IEE Proc Radar Sonar Navig, 153(6):473-481.

[14]Greco M, Stinco P, Gini F, 2010. Impact of sea clutter nonstationarity on disturbance covariance matrix estimation and CFAR detector performance. IEEE Trans Aerosp Electron Syst, 46(3):1502-1513.

[15]Guan J, Chen XL, Huang Y, et al., 2012. Adaptive fractional Fourier transform-based detection algorithm for moving target in heavy sea clutter. IET Radar Sonar Navig, 6(5):389-401.

[16]Guo Q, Yu X, Ruan GQ, 2019. LPI radar waveform recognition based on deep convolutional neural network transfer learning. Symmetry, 11(4):540.

[17]Hao CP, Orlando D, Foglia G, et al., 2014. Persymmetric adaptive detection of distributed targets in partially- homogeneous environment. Dig Signal Process, 24:42-51.

[18]Hassanieh H, Indyk P, Katabi D, et al., 2012. Simple and practical algorithm for sparse Fourier transform. Proc 23rd Annual ACM-SIAM Symp on Discrete Algorithms, p.17-19.

[19]Herselman PL, de Wind HJ, 2008. Improved covariance matrix estimation in spectrally inhomogeneous sea clutter with application to adaptive small boat detection. Proc IEEE Int Conf on Radar, p.26-30.

[20]Herselman PL, Baker CJ, de Wind HJ, 2008. An analysis of X-band calibrated sea clutter and small boat reflectivity at medium-to-low grazing angles. Int J Navig Observ, 2008:347518.

[21]Jafarzadehpour F, Molahosseini MS, Zarandi AAE, et al., 2019. Efficient modular adder designs based on thermometer and one-hot coding. IEEE Trans VLSI Syst, 27(9):2142-2155.

[22]Jay E, Ovarlez JP, Declercq D, et al., 2002. Bayesian optimum radar detector in non-Gaussian noise. Proc 26th Int Conf on Acoustics, p.13-17.

[23]Khan A, Sohail A, Zahoora U, et al., 2019. A survey of the recent architectures of deep convolutional neural networks. https://arxiv.org/abs/1901.06032

[24]Kong SH, Kim M, Hoang LM, et al., 2018. Automatic LPI radar waveform recognition using CNN. IEEE Access, 6:4207-4219.

[25]Lamont-Smith T, 2008. Azimuth dependence of Doppler spectra of sea clutter at low grazing angle. IET Radar Sonar Navig, 2(2):97-103.

[26]Lei YM, Tian YK, Shan HM, et al., 2020. Shape and margin- aware lung nodule classification in low-dose CT images via soft activation mapping. Med Image Anal, 60:101628.

[27]Li Y, He MK, Zhang N, 2017. An ionospheric clutter recognition method based on machine learning. Proc IEEE Int Symp on Antennas and Propagation & USNC/URSI National Radio Science Meeting, p.9-14.

[28]Li YZ, Xie PC, Tang ZS, et al., 2019. SVM-based sea-surface small target detection: a false-alarm-rate-controllable approach. IEEE Geosci Remote Sens Lett, 16(8):1225-1229.

[29]Liu C, Wang J, Liu XM, et al., 2019. Deep CM-CNN for spectrum sensing in cognitive radio. IEEE J Sel Areas Commun, 37(10):2306-2321.

[30]Liu J, Zhang ZJ, Yang Y, 2012. Performance enhancement of subspace detection with a diversely polarized antenna. IEEE Signal Process Lett, 19(1):4-7.

[31]Liu NB, Xu YN, Ding H, et al., 2019. High-dimensional feature extraction of sea clutter and target signal for intelligent maritime monitoring network. Comput Commun, 147:76-84.

[32]Liu S, Huang WM, Zhang Z, 2020. Person re-identification using hybrid task convolutional neural network in camera sensor networks. Ad Hoc Netw, 97:102018.

[33]Long J, Shelhamer E, Darrell T, 2015. Fully convolutional networks for semantic segmentation. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.8-10.

[34]Lv MJ, Zhou C, 2019. Study on sea clutter suppression methods based on a realistic radar dataset. Remote Sens, 11(23):2721.

[35]Ma LW, Wu JJ, Zhang JP, et al., 2020. Research on sea clutter reflectivity using deep learning model in Industry 4.0. IEEE Trans Ind Inform, 16(9):5929-5937.

[36]Mahdi A, Qin J, 2019. An extensive evaluation of deep featuresof convolutional neural networks for saliency prediction of human visual attention. J Vis Commun Image Represent, 65:102662.

[37]McDonald AM, de Wind HJ, Cilliers JE, 2010. Performance prediction for a coherent X-band radar in a maritime environment with K-distributed sea clutter. Proc IEEE Int Conf on Radar, p.1208-1213.

[38]McDonald MK, Cerutti-Maori D, 2016. Coherent radar processing in sea clutter environments, part 2: adaptive normalised matched filter versus adaptive matched filter performance. IEEE Trans Aerosp Electron Syst, 52(4):1818-1833.

[39]Pang CS, Liu SH, Han Y, 2018. High-speed target detection algorithm based on sparse Fourier transform. IEEE Access, 6:37828-37836.

[40]Ritchie M, Stove A, Woodbridge K, et al., 2016. NetRAD: monostatic and bistatic sea clutter texture and Doppler spectra characterization at S-band. IEEE Trans Geosci Remote Sens, 54(9):5533-5543.

[41]Rosenberg L, Watts S, Greco MS, 2019. Modeling the statistics of microwave radar sea clutter. IEEE Aerosp Electron Syst Mag, 34(10):44-75.

[42]Sangston KJ, Gini F, Greco MS, 2012. Coherent radar target detection in heavy-tailed compound-Gaussian clutter. IEEE Trans Aerosp Electron Syst, 48(1):64-77.

[43]Sekine M, Musha T, Tomita Y, et al., 1983. Weibull- distributed sea clutter. IEE Proc F Commun Radar Signal Process, 130(5):476.

[44]Shi SN, Liang X, Shui PL, et al., 2019. Low-velocity small target detection with Doppler-guided retrospective filter in high-resolution radar at fast scan mode. IEEE Trans Geosci Remote Sens, 57(11):8937-8953.

[45]Shnidman DA, 1999. Generalized radar clutter model. IEEE Trans Aerosp Electron Syst, 35(3):857-865.

[46]Shui PL, Liu M, 2016. Subband adaptive GLRT-LTD for weak moving targets in sea clutter. IEEE Trans Aerosp Electron Syst, 52(1):423-437.

[47]Shui PL, Shi YL, 2012. Subband ANMF detection of moving targets in sea clutter. IEEE Trans Aerosp Electron Syst, 48(4):3578-3593.

[48]Su NY, Chen XL, Guan J, et al., 2019. Deep CNN-based radar detection for real maritime target under different sea states and polarizations. Proc 4th Int Conf on Cognitive Systems and Signal Processing, p.321-331.

[49]Trunk GV, George SF, 1970. Detection of targets in non- Gaussian sea clutter. IEEE Trans Aerosp Electron Syst, ASE-6(5):620-628.

[50]Walker D, 2000. Experimentally motivated model for low grazing angle radar Doppler spectra of the sea clutter at small grazing angles. IEE Proc Radar Sonar Navig, 147(3):114-120.

[51]Walker D, 2001. Doppler modelling of radar sea clutter. IEE Proc Radar Sonar Navig, 148(2):73-80.

[52]Wang C, Wang J, Zhang XD, 2017. Automatic radar waveform recognition based on time-frequency analysis and convolutional neural network. IEEE Int Conf on Acoustics, Speech and Signal Processing, p.5-9.

[53]Wang L, Tang J, Liao QM, 2019. A study on radar target detection based on deep neural networks. IEEE Sens Lett, 3(3):7000504.

[54]Wang SG, Patel VM, Petropulu A, 2016. RSFT: a realistic high dimensional sparse Fourier transform and its application in radar signal processing. Proc IEEE Military Communications Conf, p.1-3.

[55]Wang WP, Feng Y, Shan T, 2019. A sea clutter suppression method using improved time-frequency filtering method. J Signal Process, 35(2):208-216 (in Chinese).

[56]Ward KD, 1981. Compound representation of high resolution sea clutter. Electr Lett, 17(16):561-563.

[57]Watts S, 1996. Cell-averaging CFAR gain in spatially correlated K-distributed clutter. IET Radar Sonar Navig, 143(5):321-327.

[58]Watts S, Ward KD, 1987. Spatial correlation in K-distributed sea clutter. IEE Proc F Commun Radar Signal Process, 134(6):526-532.

[59]Weinberg GV, 2012. Suboptimal coherent radar detection in a KK-distributed clutter environment. Signal Process, 2012:614653.

[60]Wu J, Wang T, Meng X, et al., 2010. Clutter suppression for airborne non-sidelooking radar using ERCB-STAP algorithm. IET Radar Sonar Navig, 4(4):497-506.

[61]Yang H, Min K, 2019. A deep approach for classifying artistic media from artworks. KSII Trans Int Inform Syst, 13(5):2558-2573.

[62]Yasotharan A, Thayaparan T, 2006. Time-frequency method for detecting an accelerating target in sea clutter. IEEE Trans Aeros Electron Syst, 42(4):1289-1310.

[63]Yu XH, Chen XL, Huang Y, et al., 2019. Radar moving target detection in clutter background via adaptive dual-threshold sparse Fourier transform. IEEE Access, 7:58200-58211.

[64]Zhang L, You W, Wu QMJ, et al., 2018. Deep learning-based automatic clutter/interference detection for HFSWR. Remote Sens, 10(10):1517.

[65]Zhang RY, Cao SY, 2019. Real-time human motion behavior detection via CNN using mmWave radar. IEEE Sens Lett, 3(2):3500104.

[66]Zhao JF, Jiang RK, Wang XT, et al., 2019. Robust CFAR detection for multiple targets in K-distributed sea clutter based on machine learning. Symmetry, 11(12):1482.

[67]Zhao JR, Wen BY, Tian YW, et al., 2019. Sea clutter suppression for shipborne HF radar using cross-loop/ monopole array. IEEE Geosci Remote Sens Lett, 16(6):879-893.

[68]Zhou BL, Khosla A, Lapedriza A, et al., 2016. Learning deep features for discriminative localization. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.2921- 2929.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE