Proceedings of the
The Nineteenth International Conference on Computational Intelligence and Security (CIS 2023)
December 1 – 4, 2023, Haikou, China
Infrared and Visible Image Fusion Based on Two-stage Optimization Model
School of Mathematics and Statistics, Xidian University, China.
ABSTRACT
Infrared and visible image fusion aims to produce an enhanced fusion image that can better highlight pivotal objectives and abundant texture features. Common fusion algorithms usually represent infrared and visible images respectively in the same way, and it is difficult to extract their prominent features completely. In this paper, a twostage fusion model is proposed, in which the first stage is the process of feature extraction and noise cancellation. It can achieve the effect of significant feature extraction and useless noise elimination. In the second stage, the fused prominent features and denoised images are input to the optimization model based on non-negative matrix factorization. Then the alternating direction method of multipliers is used to solve the global component, which can fully integrate the complementary features of infrared and visible images. The results of fusion experiments on typical data sets show that the proposed algorithm can effectively improve the performance of fusion images.
Keywords: Information fusion, Image fusion, Image processing, Two-stage optimization, Non-negative matrix factorization, Alternating direction method of multipliers.
Download PDF
School of Mathematics and Statistics, Xidian University, China.
ABSTRACT
Infrared and visible image fusion aims to produce an enhanced fusion image that can better highlight pivotal objectives and abundant texture features. Common fusion algorithms usually represent infrared and visible images respectively in the same way, and it is difficult to extract their prominent features completely. In this paper, a twostage fusion model is proposed, in which the first stage is the process of feature extraction and noise cancellation. It can achieve the effect of significant feature extraction and useless noise elimination. In the second stage, the fused prominent features and denoised images are input to the optimization model based on non-negative matrix factorization. Then the alternating direction method of multipliers is used to solve the global component, which can fully integrate the complementary features of infrared and visible images. The results of fusion experiments on typical data sets show that the proposed algorithm can effectively improve the performance of fusion images.
Keywords: Information fusion, Image fusion, Image processing, Two-stage optimization, Non-negative matrix factorization, Alternating direction method of multipliers.
Download PDF