摘要
为了优化雷达图像中的目标检测,针对极化合成孔径雷达(PolSAR)图像中杂波的存在造成了图像检测结果差的问题。为解决上述问题,采用了增强极化相似性参数和基于稀疏性的非负矩阵分解(NMF)相结合的检测方法。增强的极化相似性参数突出了某类散射机理,并增大了散射类型之间的对比度,同时二次散射增强提高了总功率分布的稀疏性,改进了NMF算法,从而实现对极化SAR图像中机场区域的检测。最后通过实测数据实验说明了所提参数及方法的有效性和优越性,为雷达图像中目标识别提供了有意义的方法。
For airport area detection in polarimetric synthetic aperture radar (PolSAR) images, a new detection method was employed, which combines an enhanced polarimetric similarity parameter and a sparsity - based nonnega- rive matrix faetorization (NMF). The enhanced polarimetric similarity parameter emphasizes some scattering mecha- nisms as well as improves the contrast between one certain scattering type and other scattering types. Meanwhile, by employing the sparsity feature of the enhanced span image, nonnegative matrix factorization (NMF) was modified to realize the airport area detection in PolSAR images. Real data experiments validate the effectiveness of this proposal.
出处
《计算机仿真》
CSCD
北大核心
2013年第10期53-57,94,共6页
Computer Simulation
关键词
极化合成孔径雷达
极化散射相似性
增强极化相似性
二次散射
非负矩阵分解
Polarimetric synthetic aperture radar
Polarimetric scattering similarity
Enhanced polarimetric simi-larity
Double - bounce scattering
Nonnegative matrix factofization (NMF)