When radar detects maritime targets, it is inevitably affected by sea clutter. When the speed of sea clutter is similar to that of low-speed targets, the processing platform cannot effectively separate and suppress the clutter, making target detection difficult. To address this issue, a fast-converging method is proposed, in which a loss function based on high-order statistics is developed on the basis of constructing a clutter model and a clutter fitting network that fits real sea-condition data, thereby effectively enabling the network to learn the amplitude distribution and correlation characteristics of real clutter. The output of the clutter fitting network is progressively input into the signal enhancement network, and the two networks form a generation-suppression joint learning framework (GSJL). Experimental results show that the clutter separation and suppression performance of the generation-suppression joint learning framework is improved. Compared with that of a CNN with the same signal enhancement network structure, the clutter suppression ratio is increased by 3 dB. And compared with that of moving target indication(MTI), the improvement factor of the signal-to-clutter ratio is increased by 0.3. Good clutter suppression effects have been achieved, proving the effectiveness of the algorithm.
JIANGQ, WUY T, LIUW J, et al. Subspace-based distributed target detection in compound-Gaussian clutter[J]. Digital Signal Processing, 2023,140:No.104141.
[2]
DAUMF. Radar handbook, 3rd edition (M.I. skolnik, Ed; 2008)(book review)[J]. IEEE Aerospace and Electronic Systems Magazine, 2008,23(5):No.41.
[3]
高增增.海杂波仿真及抑制技术研究[D].西安电子科技大学,2024:1-105.
[4]
XINGW G, LIUM C, GUIY L, et al. Research on speed measurement in MTI radars[C]//Proceedings of the 2022 2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology. Piscataway,USA:IEEE,2022:237-241.
[5]
LIJ N, LIZ Y, YANGQ, et al. Efficient matrix sparse recovery STAP method based on kronecker transform for BiSAR sea clutter suppression[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024,62:No.5103218.
[6]
CUIW C, WANGT, WANGD G, et al. Robust SR-STAP algorithms in partly calibrated arrays for airborne radar[J]. Signal Processing, 2024,219:No.109389.
[7]
QUQ Z, CHENH, LIUW J, et al. Data-driven sea clutter suppression via an image-to-image neural network and consistency loss[J]. IEEE Transactions on Aerospace and Electronic Systems, 2024,60(3):2819-2832.
[8]
ZHANGK, ZUOW M, CHENY J, et al. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017,26(7):3142-3155.
[9]
FANY F, LIC X, LID T, et al. A novel sea clutter suppression method based on neural network[C]//Proceedings of the 2021 IEEE 4th International Conference on Electronic Information and Communication Technology. Piscataway, USA: IEEE, 2021:437-440.
[10]
ZHOUH Q, FENGX, DONGZ J, et al. Application of denoising CNN for noise suppression and weak signal extraction of lunar penetrating radar data[J]. Remote Sensing, 2021,13(4):No.779.
MOUX Q, CHENX L, GUANJ, et al. Sea clutter suppression for radar PPI images based on SCS-GAN[J]. IEEE Geoscience and Remote Sensing Letters, 2021,18(11):1886-1890.
[14]
PEIJ F, YANGY, FANGZ H, et al. Sea clutter suppression for marine surveillance radar based on generative adversarial learning[C]//Proceedings of the IGARSS 2023-2023 IEEE International Geoscience and Remote Sensing Symposium. Piscataway, USA: IEEE, 2023:5202-5205.
[15]
CONTEE, LONGOM. Characterisation of radar clutter as a spherically invariant random process[J]. IEE Proceedings F (Communications, Radar and Signal Processing), 1987,134(2):No.191.
[16]
MARIERL J. Correlated K-distributed clutter generation for radar detection and track[J]. IEEE Transactions on Aerospace and Electronic Systems, 1995,31(2):568-580.
BLACKNELLD, TOUGHR J A. Parameter estimation for the K-distribution based on (z log(z))[J]. IEE Proceedings-Radar, Sonar and Navigation, 2001,148(6):309-312.