| The fusion of infrared and visible images preserves the target and scene information well,which is beneficial to subsequent research.Image fusion can be understood as an optimization problem in essence.The intelligent optimization algorithm is applied to the field of image fusion.By optimizing the fusion weight,the background information and contour details of the source image can be better preserved,which has attracted extensive attention from scholars at home and abroad.Among them,the elite strategy non-dominated genetic algorithm(NSGA-Ⅲ)has good multi-objective optimization ability due to fast non-dominated sorting and reference point mathematical model,and can better obtain the optimal solution or optimal solution.parameter.This paper mainly studies the image fusion method based on NSGA-Ⅲ.The main contents are as follows:1.Aiming at the problem that the image fusion method is easy to lose the structural information of the source image,this paper introduces an image fusion method based on Non-subsample Shearlet transform(NSST)and NSGA-Ⅲ.This method uses NSST to convert the input image into low-frequency and high-frequency sub-bands;for low-frequency sub-band fusion,this paper designs a new fusion rule based on NSGA-Ⅲ.The image is the reference image,and the NSGA-Ⅲ algorithm is used to optimize the fusion of low-frequency sub-bands;for the fusion of high-frequency sub-bands,the absolute value of the larger rule is selected.The experimental results show that the method in this chapter preserves more structural information of the source image while the target is prominent.2.Aiming at the problem of unclear details and textures caused by artificially setting parameters in the Pulse Coupled Neural Network(PCNN)image fusion method,this paper proposes an image fusion method based on NSGA-Ⅲ-PCNN.The method uses NSST to transform the input image into low-frequency sub-bands and high-frequency sub-bands;selects the low-frequency fusion rule of the gradient combined with the Laplacian energy sum;for high-frequency fusion,this paper introduces a new method based on NSGA-Ⅲ-PCNN The high-frequency fusion rules of the NSGA-Ⅲ algorithm are used to optimize the PCNN parameters to obtain the fusion high-frequency subbands.The experimental results show that the algorithm can obtain the best PCNN parameters,and the texture of the fused image is clearer. |
