红外与可见光图像配准技术研究进展  

Infrared and Visible Image Registration Technology Research Progress

作　　者：杨诗曼 孙艳丽 韩孟孟[4] 刘宁波 王中训[1,2] YANG Shiman;SUN Yanli;HAN Mengmeng;LIU Ningbo;WANG Zhongxun(School of Physics and Electronic Information,Yantai University,Yantai 264005,China;Shandong Data Open Innovation Application Laboratory of Smart Grid Advanced Technology,Yantai University,Yantai 264005,China;Naval Aviation University,Yantai 264001,China;Beijing Institute of Mechanical and Electrical Engineering,Beijing 100083,China)

机构地区：[1]烟台大学物理与电子信息学院,山东烟台264005 [2]烟台大学智慧电网先进技术山东省数据开放创新应用实验室,山东烟台264005 [3]海军航空大学,山东烟台264001 [4]北京机电工程研究所,北京100083

出　　处：《探测与控制学报》2024年第6期10-19,共10页Journal of Detection & Control

基　　金：国家自然科学基金项目(62388102,62101583,61871392);泰山学者工程项目(tsqn202211246)。

摘　　要：红外与可见光图像配准技术为目标信息的融合互补提供支持,在医学影像、军事作战、环境监测等领域都有着广泛的应用。热辐射成像和反射成像的差异导致红外与可见光图像之间的相关性较低,需要特定的配准策略和技术来克服这些挑战。因此,对红外与可见光图像配准技术研究现状进行综述,总结图像配准中的主要技术,将红外与可见光图像配准分别从传统图像配准方法和深度学习图像配准方法的角度展开分析与研究进展的总结,归纳图像配准过程中存在的问题挑战,并对未来发展进行了展望。Infrared and visible image registration technology provides support for the fusion and complementarity of target information,and has a wide range of applications in medical imaging,military operations,environmental monitoring and other fields.The differences between reflective imaging and thermal radiation imaging result in a lower correlation between infrared and visible light images,necessitating specific registration strategies and techniques to overcome these challenges.Therefore,this paper reviewed the research status.Firstly,it summarized the main technologies in image registration,and then analyzed and summarized the research progress of infrared and visible image registration from the perspective of traditional image registration and deep learning image registration.Finally,the problems and challenges existing in the process of image registration were summarized,and the future development was prospected.

关 键 词：红外图像 可见光图像 图像配准 特征 深度学习 

分 类 号：TN957[电子电信—信号与信息处理]