亮度约束下的双分支特征融合图像去雾算法
Two-Branch Feature Fusion Image Dehazing Algorithm Under Brightness Constraint
何锦清 1董秀成 2向贤明 1郭泓达 1雎雅玲1
作者信息
- 1. 西华大学电气与电子信息学院,四川 成都 610039
- 2. 西华大学电气与电子信息学院,四川 成都 610039;四川大学锦江学院电气与电子信息工程学院,四川 眉山 620860
- 折叠
摘要
为了解决雾霾天气影响图像质量的问题,提出了一个双分支特征融合图像去雾算法.首先,采用密集残差形式的数据拟合子分支增加网络深度,提取高频细节特征,采用U-Net形式的知识迁移子分支对有限数据进行知识补充.然后,利用多尺度融合模块自适应融合双分支特征以恢复高质量的去雾图像.此外,在组合损失函数中引入亮度约束,对密集雾霾区域进行更高权重赋值.最后,在合成和真实数据集上均进行测试,并与现有的FFA、GCANet等去雾算法进行对比.实验结果表明,所提算法在合成和真实雾图上的去雾效果良好,且相较于其他算法,在4个非均匀雾霾数据集上的平均峰值信噪比提升1.55 dB～10.30 dB,平均结构相似度提升0.0312～0.2440.
Abstract
In order to solve the problem of haze weather affecting image quality,this paper proposed a two-branch feature fusion image dehazing algorithm.Firstly,the data fitting branch of dense residual form increased the network depth and extracted high-frequency detail features.The knowledge transfer branch of U-Net form provided supplemental knowledge to the finite data.Then the multi-scale fusion module adaptively fused feature of two branches to recover high-quality dehazing images.In addition,brightness constraint was introduced to combined loss function to assign higher weights to the dense haze region.Finally,both synthetic and real-world datasets were used for testing and compared with existing dehazing algorithms such as FFA and GCANet.Experimental results showed that the proposed algorithm had good dehazing effect both on synthetic and real hazy images.And compared with other comparison algorithms,the average value of peak signal to noise ratio on four nonhomogeneous haze datasets was increased by 1.55 dB-10.30 dB and the average value of structural similarity was increased by 0.0312-0.2440.
关键词
非均匀去雾/密集残差/知识迁移/亮度约束/多尺度融合Key words
nonhomogeneous dehazing/dense residual/knowledge transfer/brightness constraint/multi-scale fusion引用本文复制引用
基金项目
国家自然科学基金(11872069)
四威高科-西华大学产学研联合实验室项目(2016-YF04-00044-JH)
出版年
2024
NETL
NSTL
万方数据