基于RBF神经网络的激光雷达图像滤波融合算法  

Research on Filter fusion of Laser Radar Image Based on RBF Neural Network

作　　者：孟飞[1] 杨小冈[1] 孙鹏[1] 王仕成[1] 张合新[1] 

机构地区：[1]第二炮兵工程学院301教研室,陕西西安710025

出　　处：《激光与红外》2008年第6期615-618,共4页Laser & Infrared

基　　金：国家自然科学基金项目(No.60772151)资助

摘　　要：单一算法对激光雷达图像的滤波很难达到实用的理想效果,本文分析了激光雷达图像的噪声特点和各种滤波算法的优势,提出一种基于RBF神经网络的激光雷达图像滤波融合算法,仿真的结果显示了该算法能够在噪声抑制和信息熵保持两个方面都能达到很好的效果。It is difficult to get perfect result using a single filter algorithm to deal with laser radar image. Analysis of noise model of laser radar image and dominance of three filter algorithms. A new method using image fusion algorithm to fuse laser radar image based on RBF neural network is presented. The simulation results show that the method is effective in between image noise depression and image entropy holding.

关 键 词：径向基神经网络 激光雷达图像 图像融合 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]