UWBSAR图像中的点目标检测  

Point Target Detection in UWBSAR Image

作　　者：方学立[1] 梁甸农[1] 董臻[1] 

机构地区：[1]国防科技大学电子科学与工程学院空间电子技术研究所,长沙410073

出　　处：《信号处理》2005年第3期249-251,共3页Journal of Signal Processing

基　　金：十五"国防预研基金资助(No.41307020203)

摘　　要：针对超宽带合成孔径雷达(UWBSAR)图像的某些应用场合,研究了其中的点目标检测问题,提出了一种检测算法。该算法综合运用方向依赖滤波和子图像融合提取UWBSAR图像中点目标的各向同性特征,并通过恒虚警率检测最终实现UWBSAR图像中的点目标检测。对实验数据的处理验证了该方法的有效性。To apply Ultra-Wide Band Synthetic Aperture Radar (UWBSAR) images to some particular applications (e.g. registration in image fusion, detection road via street lamps or trees, trunk clutter suppression via trunk recognition and etc), point target detection in UWBSAR images is studied, and a detection method is presented in this paper. The method extracts the isotropic scatter characteristics of point target in UWBSAR image via aspect dependent filter and sub-image fusion, and realizes the last detection step by Constant False Alarm Rate detection. The experiment results show the effectiveness of the method.

关 键 词：点目标检测 SAR图像 UWB 超宽带合成孔径雷达 恒虚警率检测 应用场合 检测算法 图像融合 综合运用 实验数据 性特征 滤波 

分 类 号：TN215[电子电信—物理电子学] TN958