Research On Fusion Of Multi-source Images

The purpose of image fusion is to construct a fused image after combining the useful information from the source images and removing the redundant parts. The fused image will be suitable for the human eye to observe or facilitate the follow-up processing. Image fusion has had a wide application in the field of aeronautics and space, military affairs, medical treatment and so on. Besides, one of the most popular research spots in recent years is the fusion of infrared image and visible light image. Infrared images can provide more detailed temperature information while visible light images contain more abundant scene details. The fusion of infrared and visible images can make up the shortage of the two and make full use of respective advantages. The research on fusion of multi-wavelength infrared image has been growing up. Therefore, this article attempts to fuse the visible light image and multi-wavelength images, and work on the results to evaluate the fusion efficiency. Firstly,the research background of multi-source images fusion is briefly introduced. And then the fusion and evaluation methods are stated. At this part, we list some examples of common used image fusion algorithm. Afterwards, a fusion method of infrared and visible images based on discrete wavelet transform is presented and comparatively analyzed with traditional methods. Finally, a fusion experiment based on contourlet transform is carried out to achieve the fusion of visible light image, LWIR image and MWIR image. By comparing experimental results we obtain the best fusion order. Seeing from the fused images and the indexes, the results of this paper is ideal and have a certain value of research.