基于局部密度聚类的雷达目标散射中心区域分割

Segmentation of Scattering Center Region of Radar Targets Based on Local Density Clustering

散射中心是描述雷达目标高频散射机理的重要特征,准确提取雷达目标散射中心参数对解析雷达目标有着极其重要的研究意义。为了提高散射中心参数计算速度,通常将整幅合成孔径雷达(synthetic aperture radar,SAR)图像分解为多个包含散射中心的小区域,对每个小区域分别进行特征提取和参数计算。根据雷达目标散射中心的特点,提出了一种基于局部密度聚类的雷达目标散射中心区域分割技术。首先,对雷达图像进行Frost滤波、基于水平集方法(level set method,LSM)的图像分割和面积滤波的一系列图像预处理获得目标感兴趣(region of interest,ROI)区域,然后对预处理后的图像利用局部密度聚类算法检测散射中心并进行区域分割。实验中,采用模拟数据和真实数据对所提方法和传统图像分割算法展开数值实验,实验结果验证了所提方法在雷达目标散射中心区域分割的有效性和优越性。

The scattering center is a key feature to describe the high-frequency scattering mechanism of radar targets,so the accurate extraction of the scattering center parameters of radar targets is of great research significance for analyzing radar targets.In order to improve the calculation speed of scattering center parameters,the whole synthetic aperture radar(SAR)image is usually decomposed into several small regions containing scattering centers,and feature extraction and parameter calculation are performed separately for each small region.According to the characteristics of radar target scattering center,a local density clustering-based radar target scattering center region segmentation technique was proposed.Based on the new method,a series of image preprocessing of Frost filtering,image segmentation based on level set method(LSM)and area filtering were performed on the radar image to obtain the target region of interest(ROI)region,and then the preprocessed image was detected by local density clustering algorithm to detect the scattering center point and perform the region segmentation.In the experiments,simulated and real data were used to carry out numerical experiments on the method proposed and the traditional image segmentation algorithm,and the experimental results verify the effectiveness and superiority of the method proposed in segmenting the scattering center region of radar targets.