基于NLEMD的红外与可见光图像融合  

Infrared and Visible Image Fusion Technology Based on NLEMD

作　　者：余月华[1] 汪鑫[1] 熊海涵[1] 王丽芳[1] 

机构地区：[1]重庆大学城市科技学院电气信息学院,重庆402167

出　　处：《重庆理工大学学报（自然科学）》2015年第7期74-78,共5页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61171158)

摘　　要：在分析传统经验模式分解和限邻域经验模式分解方法的基础上,研究了限邻域经验模式分解(NLEMD)和模糊逻辑融合准则相结合的红外与可见光图像融合方法,可克服传统经验模式分解算法速度慢和容易产生"灰度斑"的缺陷。首先将红外与可见光图像经过NLEMD分解成本征函数模式(IMF)和剩余量(Res),然后对IMF和Res选用合适的融合准则进行融合,最后将融合后的IMF和Res进行NLEMD反变换得到最终的融合图像。实验结果证明了算法的有效性。This paper analyzed traditional EMD and NLEMD, and then studied the image fusion based on NLEMD and fuzzy logic. This method can overcome the slow composition speed and the ＇ gray dot＇ defect of traditional EMD. Firstly, infrared and visible light images were decomposed into intrinsic mode function （IMF） and residual. Then, we fused the high IMF and residual through proper fusion rules to obtain the IMF and residual of fusion image. At last, the final fusion image were obtained through inverse transform of EMD. A large numbers of experiments show that infrared and visible light images fusion method combining fuzzy logic and NLEMD can obtain a better fusion image.

关 键 词：图像融合 限邻域经验模式分解 模糊逻辑 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]