激光技术的舰船类别识别
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Classification of ship category by laser technology
  • 作者:林文学
  • 英文作者:LIN Wen-xue;Hubei Polytechnic Institute;
  • 关键词:舰船类别 ; 识别方法 ; 激光技术 ; 特征向量 ; 分类器
  • 英文关键词:ship classification;;recognition method;;laser technology;;feature vector;;classifier
  • 中文刊名:JCKX
  • 英文刊名:Ship Science and Technology
  • 机构:湖北职业技术学院;
  • 出版日期:2018-06-23
  • 出版单位:舰船科学技术
  • 年:2018
  • 期:v.40
  • 基金:国家自然科学基金资助课题(11574105)
  • 语种:中文;
  • 页:JCKX201812024
  • 页数:3
  • CN:12
  • ISSN:11-1885/U
  • 分类号:71-73
摘要
针对当前舰船类别识别方法无法高精度辨识舰船类别的难题,设计了一种基于激光技术的舰船类别识别方法。首先采用激光技术采集舰船类别识别的信息,并提取舰船类别识别的特征,然后采用回声状态网络设计舰船类别识别的分类器,实现舰船类别识别,最后进行舰船类别识别的仿真模拟实验,本文方法的舰船类别识别精度超过95%,而且可以抵抗各种噪声的干扰,舰船类别识别的鲁棒性要优于对比模型,实验结果表明本文舰船类别识别方法的优越性。
        in view of the problem that ship classification recognition method can not identify ship class at high accuracy, a recognition method of ship class based on laser technology is designed. First of all, laser technology is used to collect the information of ship classification recognition, and the features of ship category recognition are extracted. Then echo state network is used to design classification classifier for ship category recognition, and ship category recognition is realized. Finally, the simulation experiment of ship classification recognition is carried out. The accuracy of ship classification recognition is more than 95%, and it can resist all kinds of noise interference and ship category recognition. Other robustness is better than the contrast model, and the experimental results show the superiority of the ship classification recognition method.
引文
[1]方石,张坚,陈朝宏.基于小波变换与BP网络的舰船磁场信号检测[J].磁性材料及器件,2011,3:56-59.
    [2]李琴.舰船辐射噪声建模及仿真模拟器的实现[J].舰船科学技术,2010,32(4):121-133.
    [3]刘尚蔚,朱小超,张永光,等.多片点云数据拼接处理技术的研究[J].水利与建筑工程学报,2014(1):121-124.
    [4]左超,鲁敏,谭志国,等.一种新的激光成像数据多视粗拼接算法[J].计算机工程与科学,2013(12):146-152.
    [5]姜礼平,姜润翔,张志宏,等.基于小波变换与支持向量机的舰船水压信号检测方法[J].武汉理工大学学报(交通科学与工程版),2008,2:283-286.
    [6]黄文华.改进回声状态网络的热点话题预测模型[J].计算机工程与应用,2014,50(14):26-30.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700