当前位置>主页 > 期刊在线 > 计算机技术 >

计算机技术21年3期

基于斜角度雨线平移的全局稀疏去雨方法研究
焦爽 1,王婧 2
(1. 长春教育学院,吉林 长春 130033;2. 长春城投智慧城建科技有限公司,吉林 长春 130015)

摘  要:针对单幅图像雨线偏离垂直方向的现象,实现了斜角度雨线平移的全局稀疏去雨模型。文章算法利用中值滤波器对雨图像进行滤波处理,得到一个初步的雨线估计,并通过转换、平移、计算竖直方向梯度等策略使雨线垂直,然后,通过三个稀疏正则项构建全局稀疏模型进行去雨,最后,将通过全局稀疏模型进行雨线去除得到的图像进行对应的逆变换操作,得到无雨图像。实验结果表明,算法可较大程度地去除雨线并保留图像的背景细节信息。


关键词:单幅图像去除雨线;斜角度雨线;稀疏正则项;细节信息



DOI:10.19850/j.cnki.2096-4706.2021.03.023


中图分类号:TP391                                    文献标识码:A                                      文章编号:2096-4706(2021)03-0086-04


Research on Global Sparse Rain Removal Method Based on Oblique Rain Line Translation

JIAO Shuang1 ,WANG Jing2

(1.Changchun Institute of Education,Changchun 130033,China; 2.Changchun Chengtou Smart City Construction Technology Co.,Ltd.,Changchun 130015,China)

Abstract:Aiming at the phenomenon that the single image rain line deviation from the vertical direction,a global sparse rain line removal model with oblique angle rain line translation is implemented. In this paper,using median filter to filter the rain image,get a preliminary rain line estimation,and through conversion,translation,calculation of vertical gradient and other strategies make the rain line vertically,and then,through three sparse regular items build global sparse model to remove rain. Finally,the image obtained by rain line removal through global sparse model is transformed to obtain rain free image. The experimental results show that the algorithm can remove the rain line to a large extent and retain the background details of the image.

Keywords:single image rain line removal;oblique rain line;sparse regular item;detail information


参考文献:

[1] CHEN Y L,HSU C T. A Generalized Low-Rank Appearance Model for Spatio-temporally Correlated Rain Streaks [C]//2013 IEEE International Conference on Computer Vision.Sydney:IEEE,2013: 1968-1975.

[2] XU J,ZHAO W,LIU P,et al. Removing rain and snow in a single image using guided filter [C]//2012 IEEE International Conference on Computer Science and Automation Engineering(CSAE). Zhangjiajie:IEEE,2012:304-307.

[3] XU J,ZHAO W,LIU P,et al. An Improved Guidance Image Based Method to Remove Rain and Snow in a Single Image [J]. Computer and Information Science,2012,5(3):49-55.

[4] 刘国庆,卢桂馥,张强 . 一种稀疏图正则化的非负低秩矩 阵分解算法 [J]. 重庆邮电大学学报(自然科学版),2020,32(2): 295-303.

[5] 焦爽 . 基于机器学习的图像雨线去除方法研究 [D]. 长春: 东北师范大学,2020.

[6] 赵伟 . 一种基于稀疏编码和字典学习改进的单幅图像去雨 方法 [J]. 现代计算机,2020(10):94-96.

[7] 周子涵 . 基于字典学习和稀疏编码的图像质量评估方法 [D]. 广州:华南理工大学,2019.

[8] SCHREIER H W,BRAASCH J R,SUTTON M A. Systematic errors in digital image correlation caused by intensity interpolation [J/OL].Optical Engineering,2000,39(11):[2020-12- 23].https://doi.org/10.1117/1.1314593.

[9] LUO Y,XU Y,JI H. Removing Rain from a Single Image via Discriminative Sparse Coding [C]//2015 IEEE International Conference on Computer Vision(ICCV).Santiago:IEEE,2015:3397-3405.

[10] LI Y,TAN R T,GUO X J,et al. Rain Streak Removal Using Layer Priors [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas:IEEE,2016:2736-2744.

[11] DENG L J,HUANG T Z,ZHAO X L,et al. A directional global sparse model for single image rain removal [J].Applied Mathematical Modelling,2018,59:662-679.


作者简介:焦爽(1991.08—),女,汉族,吉林公主岭人,助教, 硕士研究生,研究方向:图像处理及模式识别;王婧(1990.05—), 女,汉族,安徽合肥人,中级工程师,硕士研究生,研究方向:软 件工程与大数据分析。