首页 | 本学科首页   官方微博 | 高级检索  
     

基于多目标粒子群算法的多传感器图像融合
引用本文:王宪,张方生,慕鑫,柳絮青,郭玉凡.基于多目标粒子群算法的多传感器图像融合[J].光电工程,2012,39(6):102-110.
作者姓名:王宪  张方生  慕鑫  柳絮青  郭玉凡
作者单位:轻工过程先进控制教育部重点实验室(江南大学),江苏无锡,214122
摘    要:针对图像融合中参数优化的问题,提出了一种基于多目标粒子群优化算法的多传感器图像融合方法。首先采用非采样Contourlet变换(NSCT)对源图像进行多尺度、多方向分解;然后选取图像融合的客观评价指标为优化目标函数,采用多目标粒子群优化算法对低频系数的融合参数进行优化,带通方向子带系数采用取绝对值最大的融合规则;最后通过NSCT逆变换得到融合图像。分别对多聚焦图像融合和红外与可见光图像进行融合实验,并对融合图像进行主客观评价,实验结果表明,得到的融合图像具有较好的主观视觉效果和客观评价指标。

关 键 词:多传感器  图像融合  非采样Contourlet变换  多目标粒子群
收稿时间:2011/12/20

Multi-sensor Image Fusion Based on Multi-objective Particle Swarm Optimization Algorithm
WANG Xian , ZHANG Fang-sheng , MU Xin , LIU Xu-qing , GUO Yu-fan.Multi-sensor Image Fusion Based on Multi-objective Particle Swarm Optimization Algorithm[J].Opto-Electronic Engineering,2012,39(6):102-110.
Authors:WANG Xian  ZHANG Fang-sheng  MU Xin  LIU Xu-qing  GUO Yu-fan
Affiliation:(Key Laboratory of Advanced Process Control for Light Industry,Ministry of Education,(Jiangnan University),Wuxi 214122,Jiangsu Province,China)
Abstract:A novel multi-sensor image fusion method based on multi-objective particle swarm optimization is proposed to solve the parameter optimization problem in the image fusion. Firstly, the Nonsubsampled Contourlet Transform (NSCT) is used to perform multi-scale and multi-directional decomposition on the source images. Then select the objective evaluation criteria as the optimal objective function. Multi-objective particle swarm optimization algorithm is used to optimize the fusion parameters of low-frequency coefficients. For band-pass directional sub-band coefficients selection, the rule of maximum absolute value is used. Finally, the fused image is obtained through inverse transform. The algorithm has been used to merge multi-focus images and infrared and visible light images. The experimental results indicate that the fused image obtained by the proposed method has a better subjective visual effect and objective evaluation criteria.
Keywords:multi-sensor  image fusion  nonsubsampled Contourlet transform  multi-objective particle swarm
本文献已被 CNKI 万方数据 等数据库收录!
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