期刊
INFRARED PHYSICS & TECHNOLOGY
卷 71, 期 -, 页码 151-158出版社
ELSEVIER
DOI: 10.1016/j.infrared.2015.01.022
关键词
Image fusion; Visible and infrared images; MOEA/D; Multiobjective optimization
资金
- National Natural Science Foundation of China [61201416, 61472204]
- Natural Science Basic Research Project of Shaanxi Province [2014JQ8340]
- Science Research Program Project of Educational Committee of Shaanxi Province [14JS071]
Integration of images from different sensing modalities can produce information that cannot be obtained by viewing the sensor outputs separately and consecutively. In order to enhance the contrast of the fused image and reduce the loss of fine details in the process of image fusion, an innovative fusion method of visible and infrared images is presented in this paper, which uses a multiobjective evolutionary algorithm based decomposition (MOEA/D). First of all, we employ contrast pyramid (CP) decomposition into every level of each original image. Second, MOEA/D is introduced to optimize fusion coefficients, thus the weighted coefficients can be adjusted automatically according to fitness function. Finally, obtain the fused images by the weight integration of the optimal fusion coefficients and CP reconstruction. Experimental results show that the fusion algorithm proposed in this paper achieves better effect than the other fusion algorithms both in visual effect and quantitative metrics, and the fused images are more suitable for human visual or machine perception. (C) 2015 Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据