多源图像融合方法的研究综述  

A survey of fusion methods for multi-source image

作　　者：张丽霞[1,2] 曾广平 宣兆成[1] ZHANG Li-xia;ZENG Guang-ping;XUAN Zhao-cheng(School of Information Technology Engineering,Tianjin University of Technology and Education,Tianjin 300222;School of Computer & Communication Engineering,University of Science and Technology Beijing,Beijing 100083,China)

机构地区：[1]天津职业技术师范大学信息技术工程学院,天津300222 [2]北京科技大学计算机与通信工程学院,北京100083

出　　处：《计算机工程与科学》2022年第2期321-334,共14页Computer Engineering & Science

基　　金：国家自然科学基金(11772228)。

摘　　要：由于成像机理不同,多源图像有本质区别,使得其在融合过程中存在差异。在参阅了大量中外文献的基础上,对融合方法进行分类,并重点论述了各类融合方法的融合过程和典型算法,详细阐述了其关键技术。同时,深入评述了当前的评价指标和分类。最后,结合关键技术的影响因素和技术的发展状况,从数据特征、时间效率、信息提取、评估角度和方法的普适性5个方面对融合图像领域的未来发展趋势进行了展望。Due to the different imaging mechanisms,the multi-source images are essentially diffe-rent,which makes the fusion process different.Based on a large number of Chinese and foreign literature,this paper classifies fusion methods,and focuses on the fusion processes and typical algorithms of various fusion methods,and elaborates its key techniques in detail.At the same time,an in-depth review of the current evaluation indicators and classifications is carried out.Finally,combining the influencing factors of key techniques and the technology development status,the future development trend of the fusion image field is prospected from the five aspects such as data characteristics,time efficiency,information extraction,evaluation angles and universal applicability of the method.

关 键 词：图像融合 多源图像 融合方法 评价指标 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]