摘要
针对现有的深度学习去雾算法参数多,训练时间长,无法应用到实时计算机视觉系统等问题,本文提出了一种基于明暗通道的循环GAN网络(bright and dark channel CycleGAN network,BDCCN).BDCCN以CycleGAN为基础,采用固定参数和训练参数相结合方式,基于明暗通道先验理论,改进循环感知损失,实现图像去雾.实验结果表明,本文算法计算量小,收敛快,在合成数据集和真实数据集上均表现优异.
To address the problems of the existing deep-learning defogging algorithm such as the various parameters,long training time,and inability to apply to real-time computer vision systems,this study proposes a bright and dark channel CycleGAN network(BDCCN).BDCCN,based on the CycleGAN,improves the cyclic perceptual loss and achieves image defogging by combining the fixed parameters with training parameters and drawing on the priori theory of bright and dark channels.The experimental results show that the algorithm proposed in this paper,with a small amount of calculation and a fast convergence rate,performs well on both synthetic data sets and real data sets.
作者
陈平
CHEN Ping(Department of Electronic Information,Huishang Vocational College,Hefei 230022,China)
出处
《计算机系统应用》
2022年第2期191-199,共9页
Computer Systems & Applications
基金
安徽省自然科学重点项目(KJ2019A1242)。
关键词
图像去雾
循环GAN
明暗通道先验理论
感知损失
image defogging
CycleGAN
priori theory of bright and dark channels
perceptual loss
