Multiscale feature and adaptive density-based detector for targets concealed in sea clutter of shipborne HFSWR

Abstract

High-frequency surface wave radar (HFSWR) exploits high-frequency electromagnetic waves to achieve over-the-horizon maritime target detection and plays a vital role in marine resource monitoring, ocean environment sensing, and maritime security assurance. However, owing to the complex electromagnetic environment over the ocean, its target detection performance is often severely affected by various types of interferences. To address the challenging problem of target detection in sea clutter facing HFSWR, this study proposes a cascaded target detection algorithm. First, considering the complex regional morphology and significant shape variations of sea clutter in the range–doppler (RD) spectrum of the HFSWR, a lightweight multiscale feature fusion semantic segmentation method, termed multiscale lightweight SegNet (MSL-SegNet), is developed. This method effectively reduces the model parameters while maintaining high segmentation accuracy. Subsequently, for the candidate target point set obtained after cell averaging constant false alarm rate (CA-CFAR) detection and extreme learning machine (ELM) filtering, an adaptive parameter and anisotropic (APA)-DBSCAN was proposed. Experimental results based on shipborne HFSWR field data demonstrate that the proposed method achieves effective detection performance.

Keywords

High-frequency surface wave radar (HFSWR) / Image segmentation / Clustering algorithm / Target detection

References

[1] Chen JX, Zhou SH, Varshney PK, Lu J, Zheng JB, Liu H et al (2020) A sparsity based CFAR algorithm for dense radar targets. In: 2020 IEEE Radar Conference (RadarConf20). IEEE, pp 1–6

[2] de Medeiros DS, da Costa RF, Irion AD, Machado R, Saotome O (2022) High-frequency surface wave radar performance analysis for CA-CFAR algorithm in Weibull-distributed clutter. In: Proceeding of Remote Sensing of the Ocean, Sea Ice, Coastal Waters, and Large Water Regions 2022. SPIE, 1226302. https://doi.org/10.1117/12.2636035

[3] Ding Y, Zhang ZL, Hu HJ, Guan RX, Feng J, Lv ZY (2025) Multi-view subspace graph convolutional clustering for hyperspectral images. In: Graph Neural Network for Hyperspectral Image Clustering. Springer, pp 45–72

[4] Guo YM, Wang Y, Meng K, Zhu ZN. Otsu multi-threshold image segmentation based on adaptive double-mutation differential evolution. Biomimetics, 2023, 8(5): 418

[5] Han H, Zhu P, Ji L, Liu D, Ning Y (2024) Research on an improved sobel operator edge detection algorithm for inner wall rust image recognition of spiral tubes. In: 2024 IEEE 2nd International Conference on Sensors, Electronics and Computer Engineering (ICSECE). IEEE, pp 1010–1013

[6] Huang GT, Xia BX, Zhuang HM, Yan BH, Wei C, Qi SL, et al.. A comparative analysis of U-Net and Vision Transformer architectures in semi-supervised prostate zonal segmentation. Bioengineering, 2024, 11(9): 865

[7] Ikotun AM, Ezugwu AE, Abualigah L, Abuhaija B, Heming J. K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data. Inf Sci, 2023, 622: 178-210

[8] Ji YZ, Liu AJ, Song Z, Shao S, Yu CJ. HFSWR clutter suppression and target detection method based on RRN and exponential weight control. IEEE Geosci Remote Sens Lett, 2024, 21: 3507305

[9] Khan K, Ur Rehman A, Khan A, Naqvi SR, Belhaouari SB, Bermak A. A nonparametric split and kernel-merge clustering algorithm. IEEE Trans Artif Intell, 2024, 5(9): 4443-4457

[10] Li QZ, Zhang WD, Li M, Niu J, Wu QMJ. Automatic detection of ship targets based on wavelet transform for HF surface wavelet radar. IEEE Geosci Remote Sens Lett, 2017, 14(5): 714-718

[11] Lin RQ, Ren XY, Chen YW, Deng YK, Tian WM. An improved two-dimensional CFAR detector for moving target detection in complex ground clutter scenarios. IET Conf Proc, 2024, 2023(47): 974-979

[12] Lu FF, Tang C, Liu TX, Zhang ZH, Li LD. Multi-attention segmentation networks combined with the Sobel operator for medical images. Sensors, 2023, 23(5): 2546

[13] Ponsford AM, Wang J. A review of high frequency surface wave radar for detection and tracking of ships. Turk J Electri Eng Comput Sci, 2010, 18(3): 409-428

[14] Ren J, Wang JK, Chen R, Li H, Xu DL, Yan LH, et al.. Remote sensing identification of shallow landslide based on improved Otsu algorithm and multi feature threshold. Front Earth Sci, 2024, 12: 1473904

[15] Rohling H (2011) Ordered statistic CFAR technique—an overview. In: 2011 12th International Radar Symposium (IRS). IEEE, pp 631–638

[16] Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, pp 234–241. https://doi.org/10.1007/978-3-319-24574-4_28

[17] Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell, 2017, 39(4): 640-651

[18] Sun WF, Zhao LL, Li XT, Ji YG, Huang WM. Plot-to-track association using IGMM course modeling for target tracking with compact HFSWR. IEEE Geosci Remote Sens Lett, 2024, 21: 1-5

[19] Wang YM, Mao XP, Zhang J, Ji YG. Detection of vessel targets in sea clutter using in situ sea state measurements with HFSWR. IEEE Geosci Remote Sens Lett, 2018, 15(2): 302-306

[20] Wang ZZ (2025) A comparative tutorial of the histogram-based image segmentation methods. Preprint at arXiv:2502.18550

[21] Wu MK, Niu J, Zhang L, Wu QMJ, Shi CL, Zhang JZ (2021a) Target detection for RD images of HFSWR based on CNN-ELM model. In: OCEANS 2021: San Diego–Porto. IEEE, pp 1–4

[22] Wu MK, Zhang L, Niu J, Wu QMJ. Target detection in clutter/interference regions based on deep feature fusion for HFSWR. IEEE J Sel Top Appl Earth Obs Remote Sens, 2021, 14: 5581-5595

[23] Yu Y, Tang J, Xiao M, Zhang XY. A robust cross-weighted thresholding method for object extraction in complex scenes. Circuits Syst Signal Process, 2024, 43(9): 5964-5988

[24] Zhang L, Li QF, Wu QMJ. Target detection for HFSWR based on an S³ D algorithm. IEEE Access, 2020, 8: 224825-224836

[25] Zhang L, Mao DW, Niu J, Wu QMJ, Ji YG. Continuous tracking of targets for stereoscopic HFSWR based on IMM filtering combined with ELM. Remote Sens, 2020, 12(2): 272

[26] Zhang L, Zhang JZ, Niu J, Wu QMJ, Li GS. Track prediction for HF radar vessels submerged in strong clutter based on MSCNN fusion with GRU-AM and AR model. Remote Sens, 2021, 13(11): 2164

[27] Zhang XH, Wang LC, Wang ZA (2024a) Research on multi-depth image processing approach based on filtering algorithm. In: 2024 5th International Conference on Computer Vision, Image and Deep Learning (CVIDL). IEEE, pp 128–132

[28] Zhang Y, Kang NZP, Zhao B, Ren H, Hua QL, Tian J (2024b) A novel moving ship target refocusing algorithm by HFSWR information assisted SAR-GMTI system. In: IGARSS 2024—2024 IEEE International Geoscience and Remote Sensing Symposium. IEEE, pp 9182–9185

[29] Zhu QY, Hu LS, Wang SJ (2024) Image clustering algorithm based on self-supervised pretrained models and latent feature distribution optimization. Preprint at arXiv:2408.01920

Funding

National Natural Science Foundation of China(52371355)

RIGHTS & PERMISSIONS

The Author(s)