Study On Fusion Technology For Multi-sensor Images

With the development of image sensor and imaging technology, there are more and more ways to obtain different images. In order to promote the applications in various fields, the study on the multi-sensor image fusion technology becomes more and more important for scholars. Multi-sensor image fusion means combining the information of two or more source images to acquire more accurate, complete and reliable description of a same scene.In this paper, the image fusion method based on multi-resolution is discussed. The principle of image decomposition and reconstruction based on Gauss-pyramid, Laplacian-pyramid, contrast-pyramid and wavelet-pyramid is emphatically analyzed, as well as the fusion algorithm. In the experiment of image fusion based on wavelet decomposition, region-based selection and weighted fusion operators which based on traditional fusion operators are adopted, and good effect is achieved. Furthermore, image registration is also discussed. Pixel level image fusion requires image registration with precision of sub-pixel level. In order to satisfy the demand of pixel level image fusion, the method of image registration based on mutual information is adopted.According to the practical research application, a set of software, "Multi-sensor Image Fusion Software System", is developed to handle the image processing work involved in the paper. This software system can also be used in non-real-time and background process applications, such as analysis of multi-modal medical image and multi-source remote sensing image.