基于小波变换的红外与可见光图像融合

Infrared and Visible Image Fusion Based on Wavelet Transform

针对利用传统方法进行的微光条件下红外与可见光图像的融合结果彩色视觉效果差以及缺少环境细节的问题,提出一种基于二级小波变换与自适应直方图均衡化的红外与可见光图像融合算法。首先对可见光图像分别进行自适应直方图均衡化与直方图均衡化,将自适应直方图均衡化处理结果转化为HSV格式,依据视觉感官结果进行色彩修正,再与直方图均衡化结果线性加权得到处理后的可见光图像,最后将处理的可见光图像与红外图像进行二级小波变换。为了验证算法的优越性,将其与4种传统方法比较。经过一个数据集大量的实验结果证明,相较于传统方法,所提出的算法具有较好的色彩视觉效果,有效的保留了可见光的环境信息,具有较高的实用价值。

Aiming at the problems of poor color vision and lack of environmental details in the fusion of infrared and visible images under low-light conditions by traditional methods,an infrared and visible image fusion algorithm based on two-level wavelet transform and Adaptive histogram equalization is proposed.Firstly,we Adaptive histogram equalization and Histogram equalization the visible light image,and converted the Adaptive histogram equalization image into HSV format,the Histogram equalization image was obtained by linear weighting,and then the processed image was transformed into the infrared image by the second-order wavelet transform.In order to verify the superiority of the algorithm,it is compared with 4 traditional methods.A large number of experimental results on a data set show that the proposed algorithm has better color vision effect than traditional methods,and can effectively preserve the environmental information of visible light.