计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (23): 178-180.DOI: 10.3778/j.issn.1002-8331.2010.23.050

• 图形、图像、模式识别 • 上一篇    下一篇

基于遗传神经网络的背景杂波抑制技术研究

李志军1,范巧艳2,艾斯卡尔·艾木都拉2   

  1. 1.新疆大学 物理科学与技术学院,乌鲁木齐 830046
    2.新疆大学 信息科学与工程学院,乌鲁木齐 830046
  • 收稿日期:2009-01-19 修回日期:2009-03-27 出版日期:2010-08-11 发布日期:2010-08-11
  • 通讯作者: 李志军

Background clutter suppression technology based on genetic neural network

LI Zhi-jun1,FAN Qiao-yan2,Askar Hamdulla2   

  1. 1.Institute of Physics Science and Technology,Xinjiang University,Urumqi 830046,China
    2.Institute of Information Science and Technology,Xinjiang University,Urumqi 830046,China
  • Received:2009-01-19 Revised:2009-03-27 Online:2010-08-11 Published:2010-08-11
  • Contact: LI Zhi-jun

摘要: 低信噪比条件下点状运动目标的检测性能在很大程度上依赖于对红外背景杂波的抑制情况。针对遗传算法的全局搜索能力以及神经网络的非线性预测能力,提出了一种基于遗传神经网络的背景杂波抑制技术。杂波抑制后,残留噪声的高斯性和独立性通过 Kendall秩相关法和计算Friedman统计量的方法进行了验证。

关键词: 杂波抑制, 遗传算法, 神经网络, Kendall秩相关系数, Friedman统计量

Abstract: The performance of detecting point moving target under the condition of low Signal Noise Ratio(SNR) IR(Infra-
Red) images is dependent greatly on the suppression of background clutter.For the global search capability of genetic algorithm and nonlinear mapping ability of neural network,a kind of background clutter suppression technology based on genetic neural network is presented in this paper.Gaussianity and independency of residuals are also verified using Kendall rank correlation and Friedman statistic methods.

Key words: clutter suppression, genetic algorithm, neural network, Kendall rank correlation, Friedman statistic

中图分类号: