摘要
夜间图像去雾技术是图像处理和计算机视觉领域的研究热点,对航空航天、自动驾驶、交通监控等领域具有十分重要的意义。综合了近年来夜间图像去雾技术的国内外研究工作,分别从基于物理模型的传统方法和基于深度学习的方法两方面对近年来提出的典型方法进行归纳和总结,详细阐述了现有方法的优势和不足,并对一些典型的夜间去雾方法分别从主观评价和客观评价两方面进行了比较和分析。最后,展望了夜间图像去雾技术的未来研究方向,并给出了一些建议。
Removing nighttime haze technique is a research hotspot in both digital image processing and computer vision,which is of great significance in the fields of aerospace,autonomous driving and traffic monitoring.Surveyed the domestic and foreign research on nighttime image defogging in recent years,summarized from the viewpoint of the traditional methods based on physical models and the method based on deep learning.After that,illustrated those algorithms in detail and then characterized their strengths and limitations,followed by comparison and analysis from subjective and objective evaluation respectively.Finally,future research directions were prospected and some suggestions were given.
作者
沈琛
曹风云
杨雪洁
Shen Chen;Cao Fengyun;Yang Xuejie(School of Computer,Hefei Normal University,Hefei 230601,China;School of Electronics and Information,Anhui University,Hefei 230061,China;Anhui Province Key Laboratory of Simulation and Design for Electronic Information System,Hefei Normal University,Hefei 230601,China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2020年第11期101-114,共14页
Journal of Electronic Measurement and Instrumentation
基金
安徽省自然科学基金青年基金(1708085QF157)
安徽省高校优秀青年人才项目(gxyq2019068,gxyq2017050)
电子信息系统仿真设计安徽省重点实验室开放基金项目(2019ZDSYSZY06)资助
关键词
夜间去雾
大气散射模型
深度学习
图像质量评测
nighttime haze removal
atmospheric scattering model
deep learning
image quality assessment
