Multiresolution Image Fusion Algorithm Based on Probabilistic Model

One new multiresolution image fusion algorithm based on probabilistic model is developed. Suppose that there are multiple images obtained by different sensors to measure same object. First, to decompose each image into multiple subimages which buildup a multiresolution pyramid via wavelet packet transform, and to establish pixel-based subimage model on every level in the pyramid. Second, to identify parameters included in each subimage model based all measures from different sensors. Third, in each level local fusion estimate of the object subimage can be got by combining the model with a maximum posterior method. Finally, we may obtain global fusion estimate with the object image by applying orderly inverse wavelet packet transformation to every local fusion estimate from each level of the pyramid. This new approach has been effectively validated by fusing a visible image and an infrared image, which come entirely from same object