[1]李红云,高 银.基于天空区域分割和边界限制L0梯度最小化 滤波的图像去雾算法[J].南京理工大学学报(自然科学版),2020,44(02):236-245.[doi:10.14177/j.cnki.32-1397n.2020.44.02.016]
 Li Hongyun,Gao Yin.Image dehazing based on sky region segmentation and boundary constraint L0 gradient minimization filtering[J].Journal of Nanjing University of Science and Technology,2020,44(02):236-245.[doi:10.14177/j.cnki.32-1397n.2020.44.02.016]
点击复制

基于天空区域分割和边界限制L0梯度最小化 滤波的图像去雾算法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
44卷
期数:
2020年02期
页码:
236-245
栏目:
出版日期:
2020-04-30

文章信息/Info

Title:
Image dehazing based on sky region segmentation and boundary constraint L0 gradient minimization filtering
文章编号:
1005-9830(2020)02-0236-10
作者:
李红云1高 银2
1.泉州理工学院 智能制造学院,福建 晋江 362200; 2.中国科学院 泉州装备制造研究所,福建 晋江 362000
Author(s):
Li Hongyun1Gao Yin2
1.School of Intelligent Manufacturing,Quanzhou Institute of Technology,Jinjiang 362200,China; 2.Quanzhou Institute of Equipment Manufacturing,Chinese Academy of Sciences,Jinjiang 362000,China
关键词:
图像增强 天空区域分割 边界限制 L0梯度最小化滤波 暗原色理论
Keywords:
image enhancement sky region segmentation boundary constraint L0 gradient minimization filtering dark channel theory
分类号:
TP751; TP391
DOI:
10.14177/j.cnki.32-1397n.2020.44.02.016
摘要:
针对经典的暗原色理论算法在处理带有天空区域的雾天图像时会出现光晕和亮度损失的问题,该文提出基于天空区域分割和边界限制L0梯度最小化滤波的图像去雾算法。首先根据雾天图像的直方图特性分割出天空区域,求解全局大气背景光; 其次,根据辐射立方体法则推导出边界限制条件,规整得到初始透射率图像,并运用L0梯度最小化方法对透射率图像进行平滑处理; 最后,通过优化的暗原色理论模型求取增强后的图像。通过对算法的有效性、天空区域的失真和细节特征进行分析,发现该算法比改进的暗原色算法处理效果更好。
Abstract:
To deal with the problems of image hue and brightness distortion in the classic dark channel theory algorithm,the image dehazing method based on the sky region segmentation and boundary constraint L0 gradient minimization filtering is proposed here. According to the histogram property of hazy image,the sky regions are segmented to solve the global atmospheric light. Secondly,the boundary constraint equation is firstly used to normalize input image by the radiance cube to obtain the initial transmission which is smoothed by L0 gradient minimization filtering. Finally,according to the optimization of the dark channel theory,a dehazing enhancement image is obtained. Analysis of the effectiveness of the algorithm,the distortion of the sky regions and the detailed feature shows that,the method in this paper is better than the improved dark channel algorithm in term of dehazing visual effect.

参考文献/References:

[1] Wang Q,Ward R K. Fast image/video contrast enhancement based on weighted thresholded histogram equalization[J]. Consumer Electronics IEEE Transactions on,2007,53(2):757-764.
[2]王萍,张春,罗颖昕. 一种雾天图像低对比度增强的快速算法[J]. 计算机应用,2006,26(1):152-153.
Wang Ping,Zhang Chun,Luo Yingxin. Fast algorithm to enhance contrast of fog-degraded images[J]. Journal of Computer Applications,2006,26(1):152-153.
[3]Jobson D J,Rahman Z,Woodell G A. Properties and performance of a center/surround retinex[J]. IEEE Transactions on Image Processing,1997,6(3):451-462.
[4]Rahman Z U,Jobson D J,Woodell G A. Retinex processing for automatic image enhancement[J]. Proceedings of SPIE-The International Society for Optical Engineering,2004,13:100-110.
[5]Elad M,Kimmel R,Shaked D,et al. Reduced complexity Retinex algorithm via the variational approach[J]. Journal of Visual Communication and Image Representation,2003,14(4):369-388.
[6]Wanting Y,Ronggui W,Shuai F,et al. Variable filter retinex algorithm for foggy image enhancement[J]. Journal of Computer-aided Design & Computer Graphics,2010,22(6):965-971.
[7]Narasimhan S G,Nayar S K. Interactive(de)weathering of an image using physical models[C]//IEEE Workshop on Color and Photometric Methods in Computer Vision. Beijing,China:IEEE,2003:1-8.
[8]He K,Sun J,Tang X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[9]Fattal R. Single image dehazing[J]. ACM Transactions on Graphics,2008,27(3):1-9.
[10]Tarel J P,Hautiere N. Fast visibility restoration from a single color or gray level image[C]//2009 IEEE 12th International Conference on Computer Vision. Paris,France:IEEE,2009:2201-2208.
[11]Meng G,Wang Y,Duan J,et al. Efficient image dehazing with boundary constraint and contextual regularization[C]//2013 IEEE International Conference on Computer Vision. Sydney,Australia:IEEE,2013:617-624.
[12]高银,云利军,石俊生,等. 基于四阶PDE模型的暗原色理论雾天图像增强算法[J]. 南京理工大学学报,2015,39(5):544-549.
Gao Yin,Yun Lijun,Shi Junsheng,et al. Enhancement dark channel theory algorithm of fog image based on fourth-order PDE model[J]. Journal of Nanjing University of Science and Technology,2015,39(5):544-549.
[13]Cai B,Xu X,Jia K,et al. Dehaze net:An end-to-end system for single image haze removal[J]. IEEE Transactions on Image Processing,2016,25(11):5187-5198.
[14]雷琴,施朝健,陈婷婷. 基于天空区域分割的单幅海面图像去雾方法[J]. 计算机工程,2015(5):237-242.
Lei Qin,Shi Chaojian,Chen Tingting. Single sea image haze removal method based on segmentation of sky area[J]. Computer Engineering,2015(5):237-242.
[15]肖进胜,高威,邹白昱,等. 基于天空约束暗通道先验的图像去雾[J]. 电子学报,2017,45(2):346-352.
Xiao Jinsheng,Gao Wei,Zou Baiyu,et al. Image dehazing based on sky-constrained dark channel prior[J]. Acta Electronica Sinica,2017,45(2):346-352.
[16]李尧羿,杜宇超,顾振飞. 结合天空区域识别的单幅图像去雾方法[J]. 计算机工程与应用,2018,54(19):210-221.
Li Yaoyi,Du Yuchao,Gu Zhenfei. Single image dehazing method via sky region recognition[J]. Computer Engineering and Applications,2018,54(19):210-221.
[17]Jisha M,Manju K. Fusion strategy for single image dehazing[C]//2015 Global Conference on Communication Technologies(GCCT). Thuckalay,India:IEEE,2015:580-584.
[18]Gao Y,Su Y,Li Q,et al. Single fog image restoration via multi-scale image fusion[C]//2017 3rd IEEE International Conference on Computer and Communications. Chengdu,China:IEEE,2017:1873-1878.
[19]Gao Y,Su Y,Li Q,et al. Single fog image restoration with multi-focus image fusion[J]. Journal of Visual Communication and Image Representation,2018,55:586-595.
[20]He K,Sun J,Tang X. Guided image filtering[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,35(6):1397-1409.
[21]Xu L,Lu C. Image smoothing via L0 gradient minimization[J]. ACM Trans Graph,2011,30(6):1-12.
[22]Zhang S,He F,Yao J. Single image dehazing using deep convolution neural networks[C]//Pacific Rim Conference on Multimedia. Cham,Switzerland:Springer,2017:128-137.
[23]Hosseini M S,Plataniotis K N. Image sharpness metric based on maxpol convolution kernels[C]//2018 25th IEEE International Conference on Image Processing(ICIP). Athens,Greece:IEEE,2018:296-300.

相似文献/References:

[1]陈钱,顾国华,柏连发,等.微光图像实时对比度增强处理[J].南京理工大学学报(自然科学版),1997,(04):9.
 Chen Qian Gu Guohua Bai Lianfa Wang Yu.Real time Contrast Stretching in Low light level Image Processing[J].Journal of Nanjing University of Science and Technology,1997,(02):9.
[2]高 银,云利军,石俊生,等.基于四阶PDE模型的暗原色理论雾天 图像增强算法[J].南京理工大学学报(自然科学版),2015,39(05):544.
 Gao Yin,Yun Lijun,Shi Junsheng,et al.Enhancement dark channel theory algorithm of fog image based on fourth-order PDE model[J].Journal of Nanjing University of Science and Technology,2015,39(02):544.
[3]潘健鸿,高 银.基于天空区域分割和多尺度融合的单幅雾天图像复原算法[J].南京理工大学学报(自然科学版),2019,43(05):592.[doi:10.14177/j.cnki.32-1397n.2019.43.05.008]
 Pan Jianhong,Gao Yin.Single image dehazing with sky region segmentationand multi-scale fusion[J].Journal of Nanjing University of Science and Technology,2019,43(02):592.[doi:10.14177/j.cnki.32-1397n.2019.43.05.008]

备注/Memo

备注/Memo:
收稿日期:2019-04-20 修回日期:2019-08-16
基金项目:泉州理工学院智能制造工程中心校级课题(2019-ZNZZ-03); 福建省中青年教师教育科研项目(JAT191675)
作者简介:李红云(1982-),女,硕士,助教,主要研究方向:室内定位地图构建和视频图像复原,E-mail:lilinwen521@163.com; 通讯作者:高银(1985-),男,硕士,工程师,主要研究方向:图像复原、增强和融合等,E-mail:yngaoyin@163.com。
引文格式:李红云,高银. 基于天空区域分割和边界限制L0梯度最小化滤波的图像去雾算法[J]. 南京理工大学学报,2020,44(2):236-245.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2020-04-20