Research On Infrared And Visible Image Fusion Algorithm Based On NSCT

Image fusion is an image enhancement technology,which can fuse the images of a scene obtained by different sensors to generate an image containing more information about the scene.Infrared and visible image fusion is an important branch of multi-sensor image fusion.the image obtained by infrared sensor contains the thermal information of outward radiation of the object,but the resolution is usually low and the whole image is blurred;the image obtained by visible light sensor has rich detail information and high resolution.By using the image fusion technology to fuse the infrared image and the visible image,we can fuse the important information in the two images and generate an image with more abundant information.Therefore,the research on the fusion of infrared and visible images with complementary characteristics is of great significance.In this dissertation,the fusion method of infrared and visible images based on Non-subsampled Contourlet Transform(NSCT)is studied,and two methods for fusing infrared and visible images are proposed.The contents are as follows:1.A fusion method of infrared and visible images based on activity measure and intuitionistic fuzzy entropy is proposed.Firstly,the input visible image is enhanced by guided filtering,and then the infrared image and the enhanced visible image are decomposed by NSCT to get the high frequency subband and low frequency subband of the source image.in the high frequency subband,the activity measure composed of phase consistency,variation coefficient and weighted local energy is used to process the high frequency subband coefficients,and in the low frequency subbands,the intuitionistic fuzzy entropy is used to process the low frequency subband coefficients.In the experiment,the representative source images in the data set are selected for experiments to verify the effectiveness of the proposed method.Compared with several classical fusion algorithms,this method can extract the details of the image more effectively.2.An infrared and visible image fusion method based on structure tensor and Multi-resolution Singular Value Decomposition(MSVD)is proposed.Firstly,the input image is decomposed by NSCT,get the high frequency subband and low frequency subband of the source image then the high-frequency subband coefficients are processed by structure tensor and local energy,and the low-frequency subband coefficients are processed by MSVD.This method can better retain the structure information of the image,and the fusion result is more in line with the characteristics of human vision,and the effectiveness of the proposed method is proved by experiments.Figure[21]Table[2]Reference[72]...