基于可能性理论的红外与可见光视频自适应分层融合算法  

Adaptive layered fusion algorithm for infrared and visible video based on possibility theory

作　　者：吉琳娜[1] 郭小铭 杨风暴[1] JI Linna;GUO Xiaoming;YANG Fengbao(School of Information and Communication Engineering,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学信息与通信工程学院,太原030051

出　　处：《北京航空航天大学学报》2024年第10期3021-3031,共11页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家自然科学基金(61702465);山西省基础研究计划(201901D211238,202203021221104);山西省高等学校科技创新项目(2020L0264);中北大学研究生科技立项(2022180501)。

摘　　要：针对目前红外与可见光视频融合模型无法根据视频间差异特征动态调整融合策略,造成融合效果差甚至失效等问题,提出了一种基于可能性理论的红外与可见光视频的自适应分层融合算法。计算视频序列每帧中感兴趣区域的各类差异特征的幅值大小,得到每帧对应的主要差异特征;搭建分层融合框架,并确定各层变元,基于余弦相似性计算不同变元对各差异特征的融合有效度,利用可能性理论构造相应的融合有效度分布;逐层分析不同变元对各类差异特征的融合效果,选择出每层的最优变元;通过变元间的优化组合实现红外与可见光视频的自适应分层融合。实验结果表明:所提算法在保留红外典型目标和可见光结构细节等方面取得了显著的融合效果,并且在定量分析和定性评价上明显优于单一融合算法。The current infrared and visible video fusion model cannot dynamically adjust the fusion strategy according to the difference between videos,resulting in poor fusion effect or even failure.To address this issue,an adaptive layered fusion algorithm for infrared and visible video based on possibility theory was proposed.First,the magnitudes of various difference features of the region of interest in each frame of the video sequence were calculated,and the main difference features corresponding to each frame were obtained.Secondly,a layered fusion framework was built to determine the variables of each layer.The fusion effectiveness of different variables for each difference feature was calculated based on cosine similarity,and the possibility theory was used to construct the corresponding fusion effectiveness distribution.Then,the fusion effect of different variables for various difference features was analyzed layer by layer,and the optimal variable of each layer was selected.Finally,the adaptive layered fusion of infrared and visible video was realized through the optimal combination of variables.The experimental results show that the method in this paper has achieved remarkable fusion results in preserving typical infrared targets and visible structural details,and it is superior to other single fusion methods in quantitative analysis and qualitative evaluation.

关 键 词：图像处理 视频融合 自适应分层融合 可能性理论 红外视频 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]