探测与控制学报2024,Vol.46Issue(6) :10-19.DOI:10.20225/j.issn.1008-1194.20240602

红外与可见光图像配准技术研究进展

Infrared and Visible Image Registration Technology Research Progress

杨诗曼 孙艳丽 韩孟孟 刘宁波 王中训
探测与控制学报2024,Vol.46Issue(6) :10-19.DOI:10.20225/j.issn.1008-1194.20240602

红外与可见光图像配准技术研究进展

Infrared and Visible Image Registration Technology Research Progress

杨诗曼 1孙艳丽 2韩孟孟 3刘宁波 2王中训1
扫码查看

作者信息

  • 1. 烟台大学物理与电子信息学院,山东 烟台 264005;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
  • 2. 海军航空大学,山东 烟台 264001
  • 3. 北京机电工程研究所,北京 100083
  • 折叠

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.

Abstract

Infrared and visible image registration technology provides support for the fusion and complementari-ty of target information,and has a wide range of applications in medical imaging,military operations,environ-mental monitoring and other fields.The differences between reflective imaging and thermal radiation imaging re-sult 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 sum-marized,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

Key words

infrared image/visible light image/image registration/features/deep learning

引用本文复制引用

出版年

2024
探测与控制学报
中国兵工学会 西安机电信息研究所 机电工程与控制国家级重点实验室

探测与控制学报

CSTPCD北大核心
影响因子:0.267
ISSN:1008-1194
段落导航相关论文