遗传算法优化RBF网络的图像杂波抑制技术研究  

An image clutter suppression technique based on RBF neural network optimized by genetic algorithm

作　　者：范巧艳[1] 艾斯卡尔.艾木都拉[1] 

机构地区：[1]新疆大学信息科学与工程学院,新疆乌鲁木齐830046

出　　处：《激光杂志》2010年第2期11-13,共3页Laser Journal

基　　金：国家自然科学基金资助项目(No.60662002);新疆维吾尔自治区教育厅高校科研计划青年教师培育基金(No.XJEDU2008S14)

摘　　要：在红外搜索与跟踪系统中,背景杂波抑制效果将直接影响到低信噪比条件下点状运动目标的检测及跟踪性能。利用RBF神经网络的非线性映射能力和遗传算法的全局搜索机制,本文研究了一种利用遗传算法(GA)优化RBF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,背景杂波抑制效果与BP神经网络和常用的Uniform加权函数进行了比较,结果表明本文研究方法可行有效。The performance of moving point targets＇ detection and tracking under the condition of low SNR IR images is direct influenced by the suppression of background clutter in the infrared search and track system（IRST）.With the nonlinear mapping ability of RBF neural network and global search capability of Genetic Algoothm（GA）,a kind of image background clutter suppression technique based on RBF neural network optimized by genetic algorithm is presented in this paper.Gaussianity and independency of residuals are also verified using Kendall rank correlation and Friedman statistic methods.The performance of the suppression of background clutter is also compared to the BP neural network and Uniform weight function.The experiments show this method is feasible and efficient.

关 键 词：杂波抑制 神经网络 遗传算法 Kendall秩相关系数 Friedman统计量 

分 类 号：TN911.23[电子电信—通信与信息系统]