首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于多特征信息融合的海面微弱目标检测
引用本文:薛春岭,曹菲,孙庆,秦建强,冯晓伟.基于多特征信息融合的海面微弱目标检测[J].系统工程与电子技术,2022,44(11):3338-3345.
作者姓名:薛春岭  曹菲  孙庆  秦建强  冯晓伟
作者单位:1. 火箭军工程大学核工程学院, 陕西 西安 7100252. 宝鸡文理学院数学与信息科学学院, 陕西 宝鸡 721013
基金项目:国家自然科学基金(61903375);陕西省自然科学基金(2018JQ1046)
摘    要:为改善海杂波背景下雷达检测微弱目标的性能, 提出一种基于多特征信息融合的目标检测方法。首先, 在分析时域回波信号的基础上, 给出脉冲幅值离差比的概念, 并用其表征离散回波信号的尖锐度。其次, 结合回波信号的频率峰均比和局部分形度两种特征量, 构建多特征信息融合张量。然后, 采用交叉验证法训练支持向量机(support vectors machine, SVM)分类器, 并依据分类器进行目标检测。最后, 通过对实测海杂波数据的一系列实验分析, 优选了所提方案的参数。进一步与已有传统方法对比, 结果显示所提方法具有更好的鲁棒性。

关 键 词:目标检测  海杂波  信息融合  支持向量机  
收稿时间:2021-07-21

Sea-surface weak target detection based on multi-feature information fusion
Chunling XUE,Fei CAO,Qing SUN,Jianqiang QIN,Xiaowei FENG.Sea-surface weak target detection based on multi-feature information fusion[J].System Engineering and Electronics,2022,44(11):3338-3345.
Authors:Chunling XUE  Fei CAO  Qing SUN  Jianqiang QIN  Xiaowei FENG
Institution:1. Nuclear Engineering College, Rocket Force University of Engineering, Xi'an 710025, China2. School of Mathematics and Information Science, Baoji University of Arts and Sciences, Baoji 721013, China
Abstract:To improve the performance of radar weak target detection in sea clutter, a target detection method based on multi-feature information fusion is proposed. Firstly, on the basis of the analysis of time-domain returned signal, the pulse and amplitude deviation rate is defined to characterize the sharpness of discrete returned signal. Secondly, the multi-feature information fusion tensor is constructed by combining the frequency peak to average ratio and local grade of fractality of the returned signal. Thirdly, the support vectors machine (SVM) classifier is trained by cross validation, and the target is detected according to the classifier. Finally, by a series of experimental analysis of the measured sea clutter data, the parameters of the proposed scheme are optimized. Furthermore, the results show that the proposed method has better robustness compared with the existing traditional methods.
Keywords:target detection  sea clutter  information fusion  support vector machine (SVM)  
点击此处可从《系统工程与电子技术》浏览原始摘要信息
点击此处可从《系统工程与电子技术》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号