一种基于SAR图像鉴别的港口区域舰船目标新方法  

An SAR Images-Based New Method for Ship Discrimination in Harbor Region

作　　者：陈琪[1] 陆军[1] 王娜[1] 匡纲要[1] 

机构地区：[1]国防科学技术大学电子科学与工程学院,长沙410073

出　　处：《宇航学报》2011年第12期2582-2588,共7页Journal of Astronautics

基　　金：国家自然科学基金(60772045)

摘　　要：鉴于遥感卫星动态监视港口内舰船的需要,提出了一种SAR图像港口内舰船鉴别方法。针对港口内舰船目标散射特性,首先进行舰船目标鉴别特征的提取,包括已有鉴别特征的提取和新特征的提取;其次,在特征选择阶段,利用特征对目标与杂波的可分离性度量优选出鉴别效果明显的有效特征,并得到最大分离性对应的最优特征向量权重;最后,为了提高鉴别器的精度,设计了加权最小距离分类器。试验结果表明了所提方法的有效性。In view of the need of dynamically monitoring ships inside harbor through remote sensing satellite, a new method is proposed for ship discrimination in harbor region. Aiming at the scatter property of ship, discrimination features including existing features and new features are extracted firstly. Then, during the selection of features, effective features with better discrimination performance are selected based on criterion of separability, and the optimum feature weight vector corresponding to maximum separability is also acquired. Finally, in order to improve discrimination accuracy, a weighted minimum distance classifier is designed. The experimental results show the effectiveness of proposed method.

关 键 词：舰船目标 特征提取 特征选择 鉴别器 

分 类 号：TN911.73[电子电信—通信与信息系统]