摘要
针对强地杂波环境下合成孔径雷达(syntheticapertureradar,SAR)图像中的车辆目标鉴别问题,提出了一种基于变化检测量阈值分割和二维像素间隙度特征的车辆目标鉴别方法,利用像素散射强度变化等特征对SAR图像中的车辆目标进行目标鉴别可信度排序,并采用公开的车辆目标SAR图像数据集开展了仿真实验验证。仿真结果表明:利用二维像素间隙度特征向量计算得到的车辆目标鉴别可信度有3%~8%的提升。证明了所提方法的有效性。
Aiming at the identification problem of vehicle targets in synthetic aperture radar(SAR)image with strong ground clutter,an identification method of vehicle targets based on changeable detection threshold segmentation and two-dimensional pixel gap feature is proposed.The identification reliability of potential vehicle targets in SAR image is sorted by using the pixel scattering intensity variation,while simulation experiments are carried out based on public vehicle targets SAR image datasets,which proved that the identification reliability of vehicle targets counting by two-dimensional pixel gap features can be improved by 3%-8%.The effectiveness of the proposed method is proved.
作者
蔚宏轩
蔡猛
于祥祯
王树文
WEI Hongxuan;CAI Meng;YU Xiangzhen;WANG Shuwen(Shanghai Radio Equipment Research Institute,,Shanghai 201109,China)
出处
《制导与引信》
2022年第1期5-11,共7页
Guidance & Fuze
关键词
变化检测量
二维像素间隙度特征
车辆目标鉴别
地杂波
changeable detection parameter
two-dimensional pixel gap feature
vehicle target identification
ground clutter
