基于概率模型的多尺度图像融合算法

Multiresolution Image Fusion Algorithm Based on Probabilistic Model

文章给出了一种基于概率模型的多尺度图像融合新算法。首先,对不同的传感器图像分别进行小波分解,得到塔式结构子图像层;其次,基于不同传感器图像对应层上的对应像素,根据最小二乘规则估计模型参数;然后,根据贝叶斯规则进行融合图像相应像素的最大后验概率估计;最后,通过小波逆变换得到融合图像。采用该算法对可见光和红外图像进行融合,其结果与其它方法相比更有效。

One new multiresolution image fusion algorithm based on probabilistic model is developed.The main idea of the algorithm is：First,each image obtained from different sensor is decomposed into a multiresolution pyramid representation to obtain the subimage pyramids,Second,estimate the model parameters using least squares method based on the corresponding pixel of each level of the sensor image.Then,based on the model,derive estimation of the true scene using maximum a posterior method.Finally,perform inverse wavelet transformation to obtain the fusion image. Fuse the visible image and infrared image ,the result shows that the proposed algorithm is valid.