基于图像特征激励的自适应PCNN红外与可见光图像融合方法

Multi-Scale Fusion of Infrared and Visible Images Based on PCNN

为了弥补传统图像融合技术存在的对比度较低以及细节处理不全面的缺陷,针对红外和可见光图像融合算法进行了研究。主要研究了利用MATLAB软件实现对红外和可见光图像的处理和融合,采用对应像素取大值、取小值、平均值,区域能量、区域对比度比较的融合方法,并且对融合结果图像使用信息熵、标准差等评价指标进行了分析比较。结果表明,融合结果图像既保留了可见光图像的清晰的轮廓信息,同时也显示了目标物体的表面温度分布情况。

In order to improve the contrast of fusion image and preserve more image details. This thesis is aimed atstudying a fused method about infrared image and visual image. This paper is focusing on using MATLAB softwareto achieve the integration of infrared image and visual image. Moreover,using maximal or minimal pixel selection,pixel average,regional energy,regional contrast. The fusion image using information entropy,standard deviationevaluation index analysis. The results show that it not only remains the shape information of the visual image,but al-so displays the temperature distribution of objects from the infrared image.