Remote sensing image data fusion based on local deviation of wavelet packet transform

The goal of image fusion is to create new images that are more suitable for human visual perception, machine vision, object detection and target recognition. In order to adequately make use of all kinds of remote sensing image information, a new image fusion method based on local deviation of the wavelet packet transform is proposed. In fusion processing, the fused approximate coefficients are obtained by the weighted average method. For larger local deviation of each decomposed approximate coefficient, we choose a big power gene. The other approximate coefficient chooses a small one. The fused detailed coefficients are obtained by making each coefficient equal to the corresponding input image wavelet packet coefficient that has the greatest local deviation. Both the image information entropy and image clarity are employed to evaluate the performance of the remote sensing fusion algorithm. The experimental results show that the proposed method is more effective than the other methods.