摘要
雨天是一种常见的恶劣天气,雨线会严重影响物体分类、检测和分割等算法的精度。在有雨图像中,不同尺度的雨线具有相似的形状特征,因此可以利用雨线间的互补信息来协同表达雨线特征。通过构建多尺度特征金字塔结构来利用不同雨线间的相似性特征,并设计初始模块、卷积长短期记忆网络(Conv-LSTM)模块、融合模块和重构模块。此外,在融合模块中通过引入轻量的非局部机制来引导雨线特征的精融合和提取。在合成和真实的数据集上进行大量实验,对比近年4种基于深度学习的图像去雨方法,所提方法的峰值信噪比(PSNR)和结构相似性(SSIM)均有提升。实验结果表明,所提方法在保持图像原有信息的同时,能够高效地去除雨线和避免图像模糊。
Rainy day is a common severe weather,in which rain streaks seriously affect the accuracy of algorithms,such as object classification,detection,and segmentation.In a rain image,multiscale rain streaks have similar shape features,which make it possible to exploit such complementary information for the collaborative representation of rain streaks.In this study,we construct a multiscale feature pyramid structure to exploit the similarity features between different rain streaks and design the initial,convolutional long short-term memory network(Conv-LSTM),fusion,and reconstruction modules.In addition,we introduce a lightweight nonlocal mechanism in the fusion module to guide the fine fusion and removal of rain streak features.Extensive experiments were conducted on synthetic and real-world datasets.Compared with four recent deep learning-based single image deraining methods,the peak signal-to-noise ratio(PSNR)and structural similarity(SSIM)of the proposed method significantly improved.Experimental results show that the proposed method can effectively remove rain streaks and avoid image blur,while maintaining the original image information.
作者
张雪岩
庞彦伟
Zhang Xueyan;Pang Yanwei(School of Electrical and Information Engineering,Tianjin University,Tianjin 300072,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2021年第14期180-187,共8页
Laser & Optoelectronics Progress
基金
国家自然科学基金(61632081)。
关键词
图像处理
深度学习
图像去雨
特征金字塔
非局部机制
image processing
deep learning
single image deraining
feature pyramid
nonlocal mechanism
