应用光学2024,Vol.45Issue(6) :1095-1107.DOI:10.5768/JAO202445.0609001

基于深度学习的低照度图像增强算法综述

Review of low-illuminance image enhancement algorithm based on deep learning

李紫薇 刘金龙 杨慧珍 张之光
应用光学2024,Vol.45Issue(6) :1095-1107.DOI:10.5768/JAO202445.0609001

基于深度学习的低照度图像增强算法综述

Review of low-illuminance image enhancement algorithm based on deep learning

李紫薇 1刘金龙 1杨慧珍 2张之光1
扫码查看

作者信息

  • 1. 江苏海洋大学电子工程学院,江苏连云港 222005
  • 2. 金陵科技学院网络与通信工程学院,江苏南京 211169
  • 折叠

摘要

在弱光条件下拍摄的图像往往存在亮度和对比度较低、颜色失真和噪声较大等特点,严重影响人眼的主观效果,极大地限制了高阶视觉任务的性能.低照度图像增强(low illuminance image enhancement,LIIE)旨在改善这类图像的视觉效果,为后续处理提供有利条件.在诸多低照度图像增强算法中,基于深度学习的低照度图像增强成为最新的解决方案.首先梳理了基于深度学习的低照度图像增强的代表性方法;其次介绍了现有低照度图像数据集、损失函数和评价指标;再次通过基准测试与实验分析,进一步对现有基于深度学习的低照度图像增强算法进行全面评估;最后对目前研究进行总结,并对低照度图像增强的发展方向进行讨论和展望.

Abstract

Images captured under low-light conditions are often characterized by low brightness and contrast,color distortion,and high noise,which seriously affect the subjective vision of human eyes and greatly limit the performance of higher-order vision tasks.Low illuminance image enhancement(LIIE)aims to improve the visual effect of such images and provide favorable conditions for subsequent processing.Among many low-illuminance image enhancement algorithms,the LIIE based on deep learning has become the latest solution.Firstly,the representative methods for LIIE based on deep learning were reviewed.Secondly,the existing low-illuminance image datasets,loss functions,and evaluation indicators were introduced.Thirdly,the existing LIIE algorithms based on deep learning were comprehensively evaluated through benchmark testing and experimental analysis.Finally,a summary of current research was provided,and the development direction of LIIE was discussed and prospected.

关键词

低照度图像/图像增强/深度学习/损失函数/基准测试

Key words

low-illuminance images/image enhancement/deep learning/loss function/benchmark testing

引用本文复制引用

出版年

2024
应用光学
中国兵工学会 中国兵器工业第二0五研究所

应用光学

CSTPCD北大核心
影响因子:0.517
ISSN:1002-2082
段落导航相关论文