重庆邮电大学学报（自然科学版）2012，Vol.24Issue(3)：308-313,6.DOI:10.3979/j.issn.1673-825X.2012.03.008
基于特征参数稀疏表示的SAR图像目标识别
Target recognition in SAR images using sparse representation based on feature space
摘要
Abstract
Pointing at the high dimension problem in SAR images' target recognition algorithm using sparse representation in image domain,we propose a new algorithm based on feature space after analyzing SAR images' statistical characteristic. First,the generalized 2-dimensional principal component analysis(C2DPCA) feature with low-dimension and high-precision is extracted to form an over-complete dictionary. Then,2D-Fisher linear discriminate criterion is used to optimize the dictionary,which makes correlation of atoms in the same class more compact and difference of atoms between classes more a-part. Besides,optimization process cuts down complexity in sparse solving. Sparse representation coefficient of test sample is computed based on the optimal dictionary. Classification and recognition is realized according to the energy feature of coefficient. Experiment results based on MSTAR SAR image data show that,algorithm raised in this essay lowers complexity in sparse solving,and increases recognition accuracy and speed effectively within simple preprocessing of SAR images.关键词
合成孔径雷达(SAR)图像/广义二维主分量分析(G2DPCA)/目标识别/稀疏表示/移动和静止目标获取与识别(MSTAR)Key words
synthetic aperture radar image/generalized 2-dimensional principal component analysis(G2DPCA)/target recognition/sparse representation/moving and stationary target acquisition and recognition(MSTAR)分类
信息技术与安全科学引用本文复制引用
王燕霞,张弓..基于特征参数稀疏表示的SAR图像目标识别[J].重庆邮电大学学报（自然科学版）,2012,24(3):308-313,6.基金项目
航空基金(2011ZC52034) （2011ZC52034）
教育部留学回国人员科研启动基金 （）
江苏高校优势学科建设工程资助项目 （）
