结合最小颜色通道图与传播滤波的单幅图像去雾算法研究

doi:10.11959/j.issn.1000-436x.2017004

通信学报 ›› 2017, Vol. 38 ›› Issue (1): 26-34.doi: 10.11959/j.issn.1000-436x.2017004

结合最小颜色通道图与传播滤波的单幅图像去雾算法研究

汤红忠^1,^2,³,张小刚¹,朱玲^2,³,陈华⁴,王翔^2,³,李骁^2,³

¹ 湖南大学电气与信息工程学院，湖南长沙 410082
² 湘潭大学信息工程学院，湖南湘潭 411105
³ 湘潭大学控制工程研究所，湖南湘潭 411105
⁴ 湖南大学信息科学与工程学院，湖南长沙410082

修回日期:2016-10-28 出版日期:2017-01-01 发布日期:2017-01-23
作者简介:汤红忠（1979-），女，湖南衡山人，湘潭大学副教授，湖南大学博士生，主要研究方向为图像处理与模式识别、字典学习及稀疏表示。|张小刚（1972-），男，河南汝南人，湖南大学教授、博士生导师，主要研究方向为工业过程控制与模式识别。|朱玲（1990-），女，湖南娄底人，湘潭大学硕士生，主要研究方向为图像处理与模式识别。|陈华（1974-），女，广东五华人，湖南大学讲师、硕士生导师，主要研究方向为图像处理与模式识别。|王翔（1991-），男，湖南衡阳人，湘潭大学硕士生，主要研究方向为图像处理与模式识别。|李骁（1993-），男，湖南临湘人，湘潭大学硕士生，主要研究方向为图像处理与模式识别。
基金资助:
国家自然科学基金资助项目(61573299);国家自然科学基金资助项目(61673162);国家自然科学基金资助项目(61672216);国家自然科学基金资助项目(61602397);湖南省教育厅基金资助项目(15C1328)

Study of single image dehazing algorithm based on propagated filtering and minimum color channels

Hong-zhong TANG^1,^2,³,Xiao-gang ZHANG¹,Ling ZHU^2,³,Hua CHEN⁴,Xiang WANG^2,³,Xiao LI^2,³

¹ College of Electrical and Information Engineering,Hunan University,Changsha 410082,China
² College of Information Engineering,Xiangtan University,Xiangtan 411105,China
³ Institute of Control Engineering,Xiangtan University,Xiangtan 411105,China
⁴ College of Computer Science and Electronic Engineering,Hunan University,Changsha 410082,China

Revised:2016-10-28 Online:2017-01-01 Published:2017-01-23
Supported by:
The National Natural Science Foundation of China(61573299);The National Natural Science Foundation of China(61673162);The National Natural Science Foundation of China(61672216);The National Natural Science Foundation of China(61602397);Scientific Research Project of Hunan Province Education Department(15C1328)

摘要/Abstract

摘要：

针对单幅图像去雾中边缘区域去雾不彻底及黑斑现象，提出了一种结合最小颜色通道图与传播滤波的图像去雾算法。该方法首先基于双区域滤波实现大气透射率的初始估计，然后引入最小颜色通道图作为参考图像，采用传播滤波优化初始透射率，优化后的透射图因与参考图像具有相似的边缘特性，能有效避免图像景深突变边缘像素点透射率估值出现偏差的问题，同时去除了初始透射图中冗余的纹理信息，最后利用L-BFGS自适应恢复大气光矢量，基于大气散射模型复原无雾图像。实验结果表明，所提算法对图像景深突变边缘具有更为精确的透射率估算值，能有效保持边缘和细节，图像景深均匀区域具有较好的空间平滑特性，复原后的图像具有较高清晰度和丰富色彩度。

关键词: 初始透射率, 最小颜色通道图, 传播滤波, 透射率优化

Abstract:

To solve the challenging problem that the edge regions of image have some remained hazes and blackspots,a novel image dehazing algorithm was proposed based on the minimal color channel and propagated filtering.Firstly,an initial atmospheric transmission map was obtained by double-area filtering,then a minimal channel color was introduced as a reference image,and the propagated filtering was combined to optimize the initial atmospheric transmission map.Optimized transmission have the similar edge characteristics as the referenced image,so the deviation of transmission estimation can be effectively avoided for the edge pixels in the depth mutated regions,and the redundant texture information were removed in the initial transmission map.Finally,L-BFGS was used to restore atmospheric light,and the haze-free image can be recovered based on the atmospheric scattering model.Experimental results show that proposed algorithm has the more accurate transmission estimation for the depth mutated edge regions of image,so the recovered image effectively preserves the edges and details in the depth mutated regions,and has better spatial smoothness in the uniform depth regions.The recovered haze-free image with proposed method has a better sharpness and richer color degree.

Key words: initial transmission map, minimum color channel, propagated filtering, transmission optimization

中图分类号:

TP391.4

汤红忠,张小刚,朱玲,陈华,王翔,李骁. 结合最小颜色通道图与传播滤波的单幅图像去雾算法研究[J]. 通信学报, 2017, 38(1): 26-34.

Hong-zhong TANG,Xiao-gang ZHANG,Ling ZHU,Hua CHEN,Xiang WANG,Xiao LI. Study of single image dehazing algorithm based on propagated filtering and minimum color channels[J]. Journal on Communications, 2017, 38(1): 26-34.

图/表 9

图1

图2

图3

图4

图5

图6

图7

图8

表1

参考文献 23

[24]	LIU D , NOCEDAL J . On the limited memory BFGS method for large scale optimization[J]. Math Program, 1989,45(1): 503-528.
[25]	李大鹏, 禹晶, 肖创柏 . 图像去雾的无参考客观质量评测方法[J]. 中国图象图形学报, 2011,16(9): 1753-1757.
	LI D P , YU J , XIAO C B . No-reference quality assessment method for defogged images[J]. Journal of Image and Graphics, 2011,16(9): 1753-1757.
[26]	WANG J B , HE N , ZHANG L L ,et al. Single image dehazing with a physical model and dark channel prior[J]. Neurocomputing, 2015,149(PB): 718-728.
[1]	吴迪, 朱青松 . 图像去雾的最新研究进展[J]. 自动化学报, 2015,41(2): 221-239.
	WU D , ZHU Q S . The latest research progress of image dehazing[J]. Acta Automatic Sincia, 2015,41(2): 221-239.
[2]	马时平, 李权合, 张晟翀 . 一种基于反馈机制的闭环图像去雾算法[J]. 电子与信息学报, 2015,38(2): 400-407.
	MA S P , LI Q H , ZHANG S C . An adaptive closed-loop image dehazing algorithm based on the feedback mechanism[J]. Journal of Electronics ＆ Information Technology, 2015,38(2): 400-407.
[3]	FATTAL R . Dehazing using color-lines[J]. ACM Transactions on Graphics, 2014,34(1): 1-14.
[4]	毕笃彦, 眭萍, 何林远 ,等. 基于 color lines 先验的高阶马尔科夫随机场去雾[J]. 电子与信息学报, 2016,38(9): 2405-2409.
	BI D Y , XI P , HE L Y . Higher-order markov random fields defogging based on color lines[J]. Journal of Electronics ＆ Information Technology, 2016,38(9): 2405-2409.
[5]	刘海波, 杨杰, 吴正平 ,等. 基于暗通道先验和 Retinex 理论的快速单幅图像去雾方法[J]. 自动化学报, 2015,41(7): 1264-1273.
	LIU H B , YANG J , WU Z P ,et al. A fast single image dehazing method based on dark channel prior and Retinex theory[J]. Acta Automatic Sincia, 2015,41(7): 1264-1273.
[6]	BERMAN D , AVIDAN S . Non-local image dehazing[C]// IEEE Conference on Computer Vision and Pattern Recognition. 2016: 1674-1682.
[7]	KIM J Y , KIM L S , HWANG S H . An advanced contrast enhancement using partially overlapped sub-block histogram equalization[J]. IEEE Transactions on Circuits ＆ Systems for Video Technology, 2001,11(4): 475-484.
[8]	郭璠, 唐琎, 蔡自兴 . 基于融合策略的单幅图像去雾算法[J]. 通信学报, 2014,35(7): 199-207.
	GUO P , TANG J , CAI Z X . Single image defogging based on fusion strategy[J]. Journal on Communications, 2014,35(7): 199-207.
[9]	JOBSON D J , RAHMAN Z U , WOODELL G A . Properties and performance of a center/surround Retinex[J]. IEEE Transactions on Image Processing,IEEE Signal Processing Society, 1997,6(3): 451-62.
[10]	陈炳权, 刘宏立 . 基于全变分 Retinex 及梯度域的雾天图像增强算法[J]. 通信学报, 2014,35(6): 139-147.
	CHEN B Q , LIU H L . Algorithm for foggy image enhancement based on the total variational Retinex and gradient domain[J]. Journal on Communications, 2014,35(6): 139-147.
[11]	南栋, 毕笃彦, 马时平 ,等. 基于景深约束的单幅雾天图像去雾算法[J]. 电子学报, 2015,43(3): 500-504.
	NAN D , BI D Y , MA S P . Single image dehazing method based on scene depth constraint[J]. Acta Electronic Sinica, 2015,43(3): 500-504.
[12]	何人杰, 樊养余 . 基于非局部全变分正则化优化的单幅雾天图像恢复新方法[J]. 电子与信息学报, 2016,38(10): 2509-2514.
	HE R J , FAN Y Y . Novel single hazy image restoration method based on nonlocal total variation regularization optimization[J]. Journal of Electronics ＆ Information Technology, 2016,38(10): 2509-2514.
[13]	FATTAL R . Single image dehazing[J]. ACM Transactions on Graphics, 2008,27(3): 1-9.
[14]	HE K , SUN J , TANG X . Single image haze removal using dark channel prior[C]// Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2010: 2341-2353.
[15]	GIBSON K B,V? D T , NGUYEN T Q . An investigation of dehazing effects on image and video coding[J]. IEEE Transactions on Image Processing, 2012,21(2): 662-73.
[16]	HE K , SUN J , TANG X . Guided image filtering[J]. IEEE Transactions on Pattern Analysis ＆ Machine Intelligence, 2013,35(6): 1397-409.
[17]	陈书贞, 任占广, 练秋生 . 基于改进暗通道和导向滤波的单幅图像去雾算法[J]. 自动化学报, 2016,42(3): 455-465.
	CHEN S Z , REN Z G , LIAN Q S . Single image dehazing algorithm based on improved dark channel prior and guided filter[J]. Acta Automatic Sincia, 2016,42(3): 455-465.
[18]	张小刚, 陈华, 唐美玲 ,等. 一种结合双区域滤波和图像融合的单幅图像去雾算法[J]. 自动化学报, 2014,40(8): 1733-1739.
	ZHANG X G , CHEN H , TANG M L ,et al. A dehazing method in single image based on double-area filter and image fusion[J]. Acta Automatic Sincia,, 2014,40(8): 1733-1739.
[19]	NARASIMHAN S G , NAYAR S K . Chromatic framework for vision in bad weather[C]// IEEE Conference on Computer Vision ＆ Pattern Recognition. 2000: 598-605.
[20]	NARASIMHAN S G , NAYAR S K . Contrast restoration of weather degraded images[J]. IEEE Transactions on Pattern Analysis ＆ Machine Intelligence, 2003,25(6): 713-724.
[21]	CHANG J H R , WANG Y C F . Propagated image filtering[C]// IEEE Conference on Computer Vision and Pattern Recognition. 2015: 10-18.
[22]	TAN R T , . Visibility in bad weather from a single image[C]// IEEE Conference on Computer Vision and Pattern Recognition,CVPR. 2008: 1-8.
[23]	SULAMI M , GLATZER I , FATTAL R ,et al. Automatic recovery of the atmospheric light in hazy images[C]// IEEE International Conference on Computational Photography. 2014: 1-11.

图像	指标	Gibson等^[15]算法	He等^[16]算法	Zhang等^[18]算法	本文算法
	I_v	0.357 3	0.367 2	0.380 8	0.392 5
Mountain	d_sim	0.655 8	0.704 9	0.750 3	0.781 5
	avergrad	7.507 4	7.949 6	8.306 3	8.750 4
	I_v	0.501 8	0.526 1	0.537 5	0.595 3
Canyon	d_sim	0.441 3	0.462 6	0.469 1	0.469 5
	avergrad	4.692 9	4.743 2	4.713 6	4.955 3
	I_v	0.607 9	0.668 0	0.681 9	0.704 2
Train	d_sim	0.432 2	0.517 5	0.541 3	0.641 5
	avergrad	5.230 4	5.189 2	5.460 4	5.798 2
	I_v	0.198 4	0.239 9	0.219 4	0.246 8
Road	d_sim	0.342 8	0.604 3	0.647 0	0.654 6
	avergrad	11.292 0	12.725 2	12.923 5	13.056 6
	I_v	0.409 2	0.377 2	0.404 0	0.411 0
Swans	d_sim	0.580 2	0.643 3	0.657 4	0.671 2
	avergrad	7.245 4	8.022 5	8.033 0	8.254 7

结合最小颜色通道图与传播滤波的单幅图像去雾算法研究

Study of single image dehazing algorithm based on propagated filtering and minimum color channels

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 23

相关文章 15

Metrics

推荐阅读 0

[1]	刘威, 陈成, 江锐, 卢涛. 四通道无监督学习图像去雾网络[J]. 通信学报, 2022, 43(10): 210-222.
[2]	廖育荣, 王海宁, 林存宝, 李阳, 方宇强, 倪淑燕. 基于深度学习的光学遥感图像目标检测研究进展[J]. 通信学报, 2022, 43(5): 190-203.
[3]	吴德阳, 胡森, 王苗苗, 金海波, 曲长波, 唐勇. 基于区域异或和三值量化的高分辨零水印算法[J]. 通信学报, 2022, 43(2): 208-222.
[4]	张莉涓, 范明秋, 雷磊, 王勇, 袁代数. 捕获效应下基于比特检测的多分支树RFID标签识别协议[J]. 通信学报, 2021, 42(11): 205-216.
[5]	陈志旺, 张忠新, 宋娟, 雷海鹏, 彭勇. 在线目标分类及自适应模板更新的孪生网络跟踪算法[J]. 通信学报, 2021, 42(8): 151-163.
[6]	杨毅宇, 周威, 赵尚儒, 刘聪, 张宇辉, 王鹤, 王文杰, 张玉清. 物联网安全研究综述：威胁、检测与防御[J]. 通信学报, 2021, 42(8): 188-205.
[7]	陈晨, 肜娅峰, 季超群, 陈德运, 何勇军. 基于深层信息散度最大化的说话人确认方法[J]. 通信学报, 2021, 42(7): 231-237.
[8]	郭璠, 张泳祥, 唐琎, 李伟清. YOLOv3-A：基于注意力机制的交通标志检测网络[J]. 通信学报, 2021, 42(1): 87-99.
[9]	王洪雁,王拓,潘勉,汪祖民. 基于伽马范数最小化的图像去噪算法[J]. 通信学报, 2020, 41(10): 222-234.
[10]	戚琦,马迎新,王敬宇,孙海峰,廖建新. 面向算力受限边缘环境的双分支多尺度感知人脸检测网络[J]. 通信学报, 2020, 41(8): 165-174.
[11]	王晓飞,胡凡奎,黄硕. 基于分布信息直觉模糊c均值聚类的红外图像分割算法[J]. 通信学报, 2020, 41(5): 120-129.
[12]	龙华,杨明亮,邵玉斌. 基于特征流融合的带噪语音检测算法[J]. 通信学报, 2020, 41(4): 134-142.
[13]	李洪均,李超波,张士兵. 噪声稳健性的卡方生成对抗网络[J]. 通信学报, 2020, 41(3): 33-44.
[14]	丁恩杰,刘忠育,刘亚峰,郁万里. 基于多维度和多模态信息的视频描述方法[J]. 通信学报, 2020, 41(2): 36-43.
[15]	杨燕,王志伟. 基于补偿透射率和自适应雾浓度系数的图像复原算法[J]. 通信学报, 2020, 41(1): 66-75.