摘要
为了提高基于高分辨距离像(HRRP)的舰船目标识别率,首先通过目标区域提取来解决HRRP的幅度敏感性和平移敏感性的问题;然后根据传统的特征提取方法,提取出15个较好的特征进行多特征综合识别;最后在基于Fisher准则的特征选择方法上进行改进,提出了一种基于特征互补性的特征选择方法,选择一个最优特征子集。通过仿真实验验证了提出的特征选择方法,同时选择出一个最佳分类器。
In order to improve the target recognition rate of ships based on high resolution rangeprofile(HRRP),the target region of a ship is detected firstly to solve the issues of HRRP magnitudesensitivity and shift sensitivity.Next,according to the traditional feature extraction methods,15features for ship target recognition are extracted.Finally,to select an optimal subset of features,afeature selection method is proposed based on the Fisher criterion,which makes use of complementaryamong features.Simulation results shows effectiveness of the proposed method and a classifier is chosento match the selected feature set.
作者
刘巧圆
郭宝峰
王刚
杨振
赵鑫
LIU Qiao-yuan;GUO Bao-feng;WANG Gang;YANG Zhen;ZHAO Xin(School of Automation,Hangzhou Dianzi University, Hangzhou 310018,China;Nanjing Changjiang Electronic and Information Industrial Cooperation,Nanjing 340010,China)
出处
《火力与指挥控制》
CSCD
北大核心
2017年第8期82-86,共5页
Fire Control & Command Control
基金
国家自然科学基金(61375011)
浙江省自然科学基金资助项目(LY13F030015)
关键词
目标识别
HRRP
目标提取
平移敏感性
特征选择
ship target recognition
HRRP
target extraction
translation sensitivity
feature selection
