联合小波阈值和F-NLM去噪的高分辨率SAR舰船检测方法

Method of joint wavelet thresholding and F-NLM de-noising for high-resolution SAR ship detection

  • 摘要:
    目的 针对高分辨率合成孔径雷达(SAR)舰船目标多场景、多尺度、密集排布的显著特征,以及成像过程中相干噪声导致目标边缘细节模糊的问题,提出一种融合小波阈值和快速非局部均值滤波(F-NLM)去噪的高分辨率SAR舰船检测方法。
    方法 首先,利用小波阈值与F-NLM融合去噪模块预处理SAR图像,来降低海杂波噪声及增强检测目标细节特征和边缘信息,使提取的特征更具判别性。然后,选用YOLOv7检测算法结合双向特征融合模块(Bi-FPN)来对多尺度特征有效聚合,以进一步提高模型准确率。
    结果 实验结果显示,使用去噪数据集D-SSDD得到的检测平均精准度AP可达98.69%,虚警率rFAR降低至2.37%。
    结论 研究表明,所提方法不仅能均匀背景杂波提高图像质量,还能够提高多尺度特征信息的交互性,保证了目标检测精度准确。

     

    Abstract:
    Objective Aiming at the significant features of high-resolution synthetic aperture radar (SAR) ship targets with multi-scene, multi-scale and dense arrangements, and the problem of the blurring of target edge details due to coherent noise in the imaging process, a high-resolution SAR ship detection method is proposed with joint wavelet thresholding and fast non-local mean (F-NLM) de-noising.
    Methods First, wavelet thresholding and F-NLM de-noising modules are utilized to preprocess the SAR image and reduce the sea clutter noise, enhance the detailed features and edge information of the detection target, and make the extracted features more discriminative. Next, a YOLOv7 detection algorithm combined with a bi-directional feature pyramid network (Bi-FPN) is selected to effectively aggregate the multi-scale features and further improve the model's accuracy.
    Results The experimental results show that the average precision (AP) of ship detection using the de-noised dataset D-SSDD can reach 98.69% and the false alarm rate (FAR) is reduced to 2.37%.
    Conclusions It is clear that the proposed high-resolution SAR ship detection method not only homogenizes the background clutter to improve the image quality, but also improves the interactivity of multi-scale feature information to ensure precise and accurate target detection.

     

/

返回文章
返回