Research On Multi-source Image Fusion Method And Its Application

Image Fusion Technology, as an important part of the multi-sensor information fusion—the fusion of visual information, is a very popular field in recent years. Image fusion is the technique that integrates and processes the multi-source images from various sensors intelligently and obtains more accurate, complete and dependable description about the same scene than any of the individual source images. The purpose of image fusion is to utilize the complementary and redundant information in multi-source images. As a result of this processing, the fused image is more useful for human and machine perception or computer further image processing tasks.The pixel-level image fusion combines multi-source information at the basic level, and it can provide more detail information than the fusion at feature-level or decision-level. So the fused images at pixel-level fusion contain more useful information that is required in further image analysis, processing and interpretation. The pixel-level image fusion technique is the most complex in the three levels. In this thesis, most of the research works focus on the pixel-level image fusion including the various fusion methods and their implementation, the evaluation of image fusion performance and the application of the pixel-level image fusion.This dissertation concentrated on the research works listed below and achieved some creative results:(1) Put forward an image fusion algorithm based on adaptive genetic search and the selection of region character. In this method, images involved in fusion were disposed by removing yawp according to the sorting, and then decomposed by wavelet transform. The following step was to search the optimization of the size of region, and the wavelet coefficient was fused according to region character. Finally, obtained the fused image. The results show that this algorithm has good fusion effect and versatility. In the end, this algorithm is quantitatively analyzed by objective estimation standards.(2) A novel image fusion algorithm was proposed, which was based on Choquet Fuzzy Integral. The main idea was to obtain belief function using the wavelet coefficient of infrared images and low light level images, then construct fuzzy density using the fuzzy edge evaluation function of local area, finally get fused wavelet coefficient by fuzzy integral and reconstruct fused image by inverse wavelet transform. The experimental results show that the method not only keeps spectral quality of fused image, but also, enhances the spatial detail quality of fused image.(3) Considering the problems of image fusion performance evalution, the various methods of subjective and objective assessment of image fusion were researched and analyzed systematically, and the synthetic evalution criterions of image fusion were founded. These evaluation criteria were applied to compare the performance of the two novel image fusion approaches present in this dissertation. Finally, fused image based on fuzzy integral was applied in target detection. Those factual applications imply that fused images take on significance and practicability.