摘要
提出了一种基于特征融合的军事目标检测方法,充分考虑了SAR与光学图像中目标的互补性特征。目标在高分辨率SAR图像中会产生强后向散射回波(radar cross sections,RCS),因此可以快速检测出感兴趣目标。但受相干斑和人造杂波影响,检测结果存在大量虚警。相比而言,从光学图像中提取出的目标形状信息更有利于鉴别虚假。因此,本方法在串行融合结构中结合SAR和光学图像中提取出的目标特征进行融合鉴别,有效去除虚警。实验用机载测试图像对本文方法的性能进行了验证和分析。
A feature fusion based military target detection method is proposed, which takes advantage of the complementary target features in synthetic aperture radar (SAR) and optical images. With high spatial resolution SAR images, it is easy to detect interested targets fast because of the strong radar cross sections (RCS) of them compared to background. However, the false alarm rate of detection in SAR images will be high due to speckle and manmade clutters. In contrast, the shape features of targets extracted from optical images are propitious to discriminate false alarms. Therefore, in the serial structure, the proposed method combines the targerms features from SAR and optical images together to feature-fusion discrimination, reducing the false alarms effectively. Experiments with airborne images are carried out to validate and analyze the proposed method.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2007年第6期844-847,共4页
Systems Engineering and Electronics
基金
国防预研项目资助课题(41322020201)
关键词
目标检测
鉴别
特征融合
加权马氏距离
target detection
discrimination
feature fusion
weighted M-distance