Improved algorithm for image haze removal based on dark channel priority

被引：16
作者：
Huang, Chengquan [1 ]
Yang, Dong [1 ]
Zhang, Ruliang [2 ]
Wang, Lin [2 ]
Zhou, Lihua [3 ]
机构：
[1] Guizhou Minzu Univ, Engn Training Ctr, Guiyang 550025, Guizhou, Peoples R China
[2] Guizhou Minzu Univ, Key Lab Pattern Recognit & Intelligence Syst, Guiyang 550025, Guizhou, Peoples R China
[3] Guizhou Minzu Univ, Informat & Data Ctr, Guiyang 550025, Guizhou, Peoples R China
来源：
COMPUTERS & ELECTRICAL ENGINEERING | 2018年 / 70卷
关键词：
Image haze removal; Dark channel prior; Transmittance; Color distortion; Statistics;
D O I：
10.1016/j.compeleceng.2017.09.018
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
An improved algorithm is proposed for image haze removal based on dark channel priority to avoid the color distortion of haze removing about sky, white cloud or bright areas. The improved algorithm is mainly reflected in the following two aspects. One is the refined atmospheric transmittance of the hazy images with non-sky obtained using guided filter. The other is that the atmospheric transmittance of the hazy images with the sky, white cloud or the bright areas is estimated by a variety of classified statistics for haze-free outdoor images with non-sky or the haze-free outdoor images with sky. Compared with He algorithm, the weakness of atmospheric transmission of the hazy images with the sky, white cloud or the bright areas is remedied. Experimental results show that the improved algorithm is efficient to image haze removal. (C) 2017 Elsevier Ltd. All rights reserved.
引用
收藏
页码：659 / 673
页数：15
相关论文
共 14 条
[1]  
[Anonymous], 2013, Applied Statistics and Probability for Engineers
[2]  
Earll McCartney, 1976, OPTICS ATMOSPHERE SC
[3]   Single image dehazing [J].
Fattal, Raanan .
ACM TRANSACTIONS ON GRAPHICS, 2008, 27 (03)
[4]  
He KM, 2011, IEEE T PATTERN ANAL, V33, P2341, DOI 10.1109/TPAMI.2010.168
[5]   Guided Image Filtering [J].
He, Kaiming ;
Sun, Jian ;
Tang, Xiaoou .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (06) :1397-1409
[6]   Factorizing Scene Albedo and Depth from a Single Foggy Image [J].
Kratz, Louis ;
Nishino, Ko .
2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, :1701-1708
[7]   A review on dark channel prior based image dehazing algorithms [J].
Lee, Sungmin ;
Yun, Seokmin ;
Nam, Ju-Hun ;
Won, Chee Sun ;
Jung, Seung-Won .
EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2016, :1-23
[8]   A closed-form solution to natural image matting [J].
Levin, Anat ;
Lischinski, Dani ;
Weiss, Yair .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2008, 30 (02) :228-242
[9]   Efficient Image Dehazing with Boundary Constraint and Contextual Regularization [J].
Meng, Gaofeng ;
Wang, Ying ;
Duan, Jiangyong ;
Xiang, Shiming ;
Pan, Chunhong .
2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2013, :617-624
[10]   Investigating Haze-relevant Features in A Learning Framework for Image Dehazing [J].
Tang, Ketan ;
Yang, Jianchao ;
Wang, Jue .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :2995-3002
12