Sea clutter suppression via cuttable encoder-decoder-augmentation network

doi:10.23919/JSEE.2024.000096

Journal of Systems Engineering and Electronics ›› 2024, Vol. 35 ›› Issue (6): 1428-1440.doi: 10.23919/JSEE.2024.000096

• • 上一篇

收稿日期:2023-01-03 出版日期:2024-12-18 发布日期:2025-01-14

Sea clutter suppression via cuttable encoder-decoder-augmentation network

Chuanfei ZANG¹(), Yumiao WANG¹(), Xiang WANG¹(), Congan XU²^,³(), Guolong CUI¹^,*()

¹ School of Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
² Advanced Technology Research Institute, Beijing Institute of Technology, Jinan 250300, China
³ Naval Aviation University, Yantai 264000, China

Received:2023-01-03 Online:2024-12-18 Published:2025-01-14
Contact: Guolong CUI E-mail:zangcf2017@163.com;wangyumiao@std.uestc.edu.cn;w_xiang@std.uestc.edu.cn;xcatougao@163.com;cuiguolong@uestc.edu.cn
About author:
ZANG Chuanfei was born in 1999. He received his B.S. degree in Jilin University, Changchun, China, in 2021. He is currently pursuing his Ph.D. degree in University of Electronic Science and Technology of China, Chengdu, China. His research interests include target detection and deep learning. E-mail: zangcf2017@163.com

WANG Yumiao was born in 1996. She received her B.S. degree in Nanchang Hangkong University, Nanchang, China, in 2018. She is currently pursuing her Ph.D. degree in University of Electronic Science and Technology of China, Chengdu, China. Her research interests include target detection, sea clutter suppression, and deep learning. E-mail: wangyumiao@std.uestc.edu.cn

WANG Xiang was born in 1997. He received his B.S. degree in Anhui University, Hefei, China, in 2019. He is currently pursuing his Ph.D. degree in University of Electronic Science and Technology of China, Chengdu, China. His research interests include radar signal processing and machine learning. E-mail: w_xiang@std.uestc.edu.cn

XU Congan was born in 1987. He received his M.S. and Ph.D. degrees from Naval Aviation University, Yantai, China, in 2013 and 2016, respectively. He is currently a lecturer in Naval Aviation University. His research interests include intelligent perception and fusion, deep learning and its application. E-mail: xcatougao@163.com

CUI Guolong was born in 1982. He received his B.S. degree in electronic information engineering, M.S. and Ph.D. degrees in signal and information processing from the University of Electronic Science and Technology of China, Chengdu, China, in 2005, 2008, and 2012, respectively. He is currently a professor in University of Electronic Science and Technology of China. His research interests include cognitive radar, array signal processing, and through-the-wall radar. E-mail: cuiguolong@uestc.edu.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (62271126).

摘要/Abstract

Abstract:

This paper considers the problem of sea clutter suppression. We propose the cuttable encoder-decoder-augmentation network (CEDAN) to improve clutter suppression performance by enriching the contrast information between the target and clutter. Specifically, the plug-and-play residual U-block (ResUblock) is proposed to augment the feature representation ability of the clutter suppression model. The CEDAN first extracts and fuses the multi-scale features using the encoder and the decoder composed of the ResUblocks. Then, the fused features are processed by the contrast information augmentation module (CIAM) to enhance the diversity of target and clutter, resulting in encouraging sea clutter suppression results. In addition, we propose the result-consistency loss to further improve the suppression performance. The result-consistency loss enables CEDAN to cut some blocks of decoder and CIAM to reduce the inference time without significantly degrading the suppression performance. Experimental results on measured and simulated data show that the CEDAN outperforms state-of-the-art sea clutter suppression methods in sea clutter suppression performance and computation efficiency.

Key words: radar, sea clutter suppression, deep learning

. [J]. Journal of Systems Engineering and Electronics, 2024, 35(6): 1428-1440.

Chuanfei ZANG, Yumiao WANG, Xiang WANG, Congan XU, Guolong CUI. Sea clutter suppression via cuttable encoder-decoder-augmentation network[J]. Journal of Systems Engineering and Electronics, 2024, 35(6): 1428-1440.

图/表 17

参考文献 41

1	CHEN X L, GUAN J, HUANG Y, et al Radon-linear canonical ambiguity function-based detection and estimation method for marine target with micromotion. IEEE Trans. on Geoscience and Remote Sensing, 2014, 53 (4): 2225- 2240.
2	PAN M Y, SUN J, YANG Y H, et al M-FCN based sea-surface weak target detection. Journal of Systems Engineering and Electronics, 2021, 32 (5): 1111- 1118. doi: 10.23919/JSEE.2021.000095
3	XU C, HE Z S, LIU H C, et al Bayesian track-before-detect algorithm for nonstationary sea clutter. Journal of Systems Engineering and Electronics, 2021, 32 (6): 1338- 1344. doi: 10.23919/JSEE.2021.000113
4	LI Y, ZHANG N, YANG Q Characteristic-knowledge-aided spectral detection of high frequency first-order sea echo. Journal of Systems Engineering and Electronics, 2009, 20 (4): 718- 725.
5	YANG W, ZHANG L, YANG L R, et al A general evaluation system for optimal selection performance of radar clutter model. Journal of Systems Engineering and Electronics, 2022, 34 (6): 1520- 1525.
6	ZHU Y P, WEI Y S, TONG P First order sea clutter cross section for bistatic shipborne HFSWR. Journal of Systems Engineering and Electronics, 2017, 28 (4): 681- 689. doi: 10.21629/JSEE.2017.04.07
7	SHEN X L, SONG Z Y, ZHU Y F, et al Fractal detector design and application in maritime target detection. Journal of Systems Engineering and Electronics, 2017, 28 (1): 27- 35. doi: 10.21629/JSEE.2017.01.04
8	PAN M Y, SUN J, YANG Y H, et al Improved TQWT for marine moving target detection. Journal of Systems Engineering and Electronics, 2020, 31 (3): 470- 481. doi: 10.23919/JSEE.2020.000029
9	XU S W, MA Y T, BAI X H. Small target detection method in sea clutter based on interframe multi-feature iteration. Proc. of the IEEE 6th International Conference on Signal and Image Processing, 2021: 82–87.
10	ZHAO W J, JIN M L, CUI G L, et al Eigenvalues-based detector design for radar small floating target detection in sea clutter. IEEE Geoscience and Remote Sensing Letters, 2021, 19 (1): 1- 5.
11	XU S W, ZHENG J B, PU J, et al Sea-surface floating small target detection based on polarization features. IEEE Geoscience and Remote Sensing Letters, 2018, 15 (10): 1505- 1509.
12	XUE J, XU S W, LIU J, et al Bayesian detection for radar targets in compound-gaussian sea clutter. IEEE Geoscience and Remote Sensing Letters, 2022, 19 (1): 4020805.
13	SUN Z, CHEN H X, LI X L, et al. Airborne radar coherent integration and sea-clutter suppression method for marine moving target via TSLRT-MFP-SVD. Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2022: 3724–3727.
14	CHEN X L, HUANG Y, GUAN J, et al. Sea clutter suppression and moving target detection method based on clutter map cancellation in FRFT domain. Proc. of the IEEE CIE International Conference on Radar, 2011: 438–441.
15	XUE J, MA M S, LIU J, et al Wald-and rao-based detection for maritime radar targets in sea clutter with lognormal texture. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60 (1): 1- 9.
16	XU S W, WANG Z X, BAI X H, et al Optimum and near-optimum coherent CFAR detection of radar targets in compound-gaussian clutter with generalized inverse Gaussian texture. IEEE Trans. on Aerospace and Electronic Systems, 2021, 58 (3): 1692- 1706.
17	POON M W, KHAN R H, LE-NGOC S A singular value decomposition (SVD) based method for suppressing ocean clutter in high frequency radar. IEEE Trans. on Signal Processing, 1993, 41 (3): 1421- 1425. doi: 10.1109/78.205747
18	WANG Z T, WANG Y L, DUAN K Q, et al Subspace-augmented clutter suppression technique for STAP radar. IEEE Geoscience and Remote Sensing Letters, 2016, 13 (3): 462- 466.
19	ZHOU G J, JIN Y G, DONG H C, et al HF radar sea clutter rejection by nonlinear projections. Journal of Systems Engineering and Electronics, 2005, 16 (4): 733- 737.
20	CHEN X L, GUAN J, BAO Z H, et al Detection and extraction of target with micromotion in spiky sea clutter via short-time fractional Fourier transform. IEEE Trans. on Geoscience and Remote Sensing, 2013, 52 (2): 1002- 1018.
21	WANG X L, ABOUTANIOS E, AMIN M G. Slow radar target detection in heterogeneous clutter using thinned space-time adaptive processing. IET Radar, Sonar & Navigation, 2016, 10(4): 726–734.
22	FAN Y F, LI C X, LI D T, et al. A novel sea clutter suppression method based on neural network. Proc. of the IEEE 4th International Conference on Electronic Information and Communication Technology, 2021: 437–440.
23	NI Z K, SHI C, PAN J, et al Declutter-gan: GPR b-scan data clutter removal using conditional generative adversarial nets. IEEE Geoscience and Remote Sensing Letters, 2022, 19 (1): 4023105.
24	ZHAO Z X, CHEN X, LI B, et al Range-Doppler spectrograms-based clutter suppression of HF passive bistatic radar by D-CycleGAN. IEEE Sensors Journal, 2021, 21 (22): 26006- 26013. doi: 10.1109/JSEN.2021.3119747
25	MOU X Q, CHEN X L, GUAN J, et al Sea clutter suppression for radar PPI images based on SCS-GAN. IEEE Geoscience and Remote Sensing Letters, 2020, 18 (11): 1886- 1890.
26	PEI J F, YANG Y, WU Z B, et al A sea clutter suppression method based on machine learning approach for marine surveillance radar. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15 (1): 3120- 3130.
27	QIAN L. Radar clutter suppression solution based on ICA. Proc. of the Fourth International Conference on Intelligent Systems Design and Engineering Applications, 2013: 429–432.
28	ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein generative adversarial networks. Proc. of the International Conference on Machine Learning, 2017: 214–223.
29	GULRAJANI I, AHMED F, ARJOVSKY M, et al. Improved training of wasserstein gans. Proc. of the Advances in Neural Information Processing Systems, 2017: 30−45.
30	WANG Y M, ZHAO W J, WANG X, et al Nonhomogeneous sea clutter suppression using complex-valued U-Net model. IEEE Geoscience and Remote Sensing Letters, 2022, 19, 1- 5.
31	RONNEBERGER O, FISHER P, BROX T. U-net: convolutional networks for biomedical image segmentation. Proc. of the Medical Image Computing and Computer-Assisted Intervention, 2015: 234–241.
32	STROGATZ S H Exploring complex networks. Nature, 2001, 410 (6825): 268- 276. doi: 10.1038/35065725
33	CHEN X L, YU X H, HUANG Y, et al Adaptive clutter suppression and detection algorithm for radar maneuvering target with high-order motions via sparse fractional ambiguity function. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13 (1): 1515- 1526.
34	YU J G, XIA G S, DENG J J, et al Small object detection in forward-looking infrared images with sea clutter using context-driven Bayesian saliency model. Infrared Physics & Technology, 2015, 73 (1): 175- 183.
35	ZHANG L, DAI J, LU H C, et al. A bi-directional message passing model for salient object detection. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1741–1750.
36	LU S J, LIM J H. Saliency modeling from image histograms. Proc. of the European Conference on Computer Vision, 2012: 321–332.
37	LONG J T, SHELLHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3431–3440.
38	LIU N B, DING H, HUNAG Y, et al Annual progress of the sea-detecting X-band radar and data acquisition program. Journal of Radars, 2021, 10 (1): 173- 182.
39	LIU N B, DONG Y L, WANG G Q, et al Sea-detecting X-band radar and data acquisition program. Journal of Radars, 2019, 8 (5): 656- 667.
40	GLOROT X, BENGIO Y. Understanding the difficulty of training deep feedforward neural networks. Proc. of the 13th International Conference on Artificial Intelligence and Statistics, 2010: 249–256.
41	DIEDERIK P K. Adam: a method for stochastic optimization. Proc. of the International Conference on Learning Representations, 2015: 1–13.

Parameter	Value
${f_c}$/GHz	9.4
${f_s}$/MHz	60
$B$/MHz	25
${T_r}$/kHz	3
${T_p}$/μs	3
$Q$	25

Dataset	Number of samples	Target	Clutter
Training (−15 dB to 8 dB)	276	Simulated	Real
Validation (−15 dB to 8 dB)	276	Simulated	Real
Test (−20 dB to 20 dB)	8200	Simulated	Real

Block	$ {{{C}}_{{\text{in}}}} $	$ M $	$ {{{C}}_{{\text{out}}}} $
Encoder ResUblock-7	1	32	64
Encoder ResUblock-6	64	32	128
Encoder ResUblock-5	128	64	256
Encoder ResUblock-4	256	128	512
Encoder ResUblock-4D	512	256	512
Decoder ResUblock-4D	1024	256	512
Decoder ResUblock-4	1024	128	256
Decoder ResUblock-5	512	64	128
Decoder ResUblock-6	256	32	64
Decoder ResUblock-7	128	16	64

Model	CEDAN	CEDAN S2	Unet [31]	CV-UNet [30]
Params	44.01×10⁶	43.86×10⁶	31.04×10⁶	62.06×10⁶
MACs	91.89×10⁹	75.09×10⁹	133.45×10⁹	532.89×10⁹
Time/ms	19.50	14.83	16.59	63.26

Data name	File name	Target	Sea condition
data1	20210106150614_01_staring.mat	Target1	3-4
data2	20210106150614_02_staring.mat	Target1	3-4
data4	20210106150614_03_staring.mat	Target1	3-4
data5	20210106160919_01_staring.mat	Target2	3-4
data6	20210106160919_01_staring.mat	Target2	3-4

Sea clutter suppression via cuttable encoder-decoder-augmentation network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 41

相关文章 0

编辑推荐

Metrics

本文评价

Dataset	Source data	Number of samples	Target
Training	20210106150614_01_staring.mat 20210106160919_01_staring.mat	100 50	Target1 Target2
Validation	20210106150614_01_staring.mat 20210106160919_01_staring.mat	50 50	Target1 Target2
Test	20210106150614_03_staring.mat 20210106160919_02_staring.mat	9 25	Target1 Target2