基于梯度塔形分解的多传感器图像融合  

Multi-sensor Image Fusion Scheme Based on Gradient Pyramid Decomposition

作　　者：刘贵喜[1] 赵曙光[1] 杨万海[1] 

机构地区：[1]西安电子科技大学电子工程学院,西安710071

出　　处：《光电子．激光》2001年第3期293-296,共4页Journal of Optoelectronics·Laser

基　　金：国防科技预研基金资助项目 (99J16.2 .2 .DZ0 14 7)

摘　　要：给出了基于梯度塔形分解的像素级图像融合新方法。基本思想是 ,先对原图像进行梯度塔形分解 ;其次 ,按照融合规则 ,采用基于区域特性选择的加权算子去构造融合图像对应的梯度金字塔 ;最后 ,通过逆梯度塔形变换重构融合图像。该方法被成功地用于图像的融合处理。实验结果表明 ,该融合方法十分有效 ,获得的融合图像更符合人的视觉特性、更有利于机器视觉。A novel pixel-level image fusion scheme based on gradient pyramid decomposition is presented. The basic idea is to perform a gradient pyramid decomposition on each source image firstly, and then the gradient pyramid of fused image is constructed using region-based weighted operators according to different fusion rules. Finally the fused image is obtained by taking inverse gradient pyramid transform. This approach has been successfully used in image fusion. Experimental results show that the fusion scheme is effectual and the fused images are more suitable for human visual or machine perception.

关 键 词：图像融合 多传感器融合 梯度塔形分解 图像处理 

分 类 号：TN911.73[电子电信—通信与信息系统] TP212[电子电信—信息与通信工程]