A single image dehazing method based on decomposition strategy

doi:10.23919/JSEE.2022.000029

Journal of Systems Engineering and Electronics ›› 2022, Vol. 33 ›› Issue (2): 279-293.doi: 10.23919/JSEE.2022.000029

收稿日期:2020-09-16 接受日期:2022-02-22 出版日期:2022-05-06 发布日期:2022-05-06

A single image dehazing method based on decomposition strategy

Chaoxuan QIN^1,²(), Xiaohui GU^1,*()

¹ School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
¹ Southwest Technology and Engineering Research Institute, Chongqing 400039, China

Received:2020-09-16 Accepted:2022-02-22 Online:2022-05-06 Published:2022-05-06
Contact: Xiaohui GU E-mail:qinchaoxuan1991@163.com;gxiaohui@njust.edu.cn
About author:|QIN Chaoxuan was born in 1991. He received his B.S. degree from the School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, China, in 2014. He received his Ph.D. degree from the School of Mechanical Engineering, Nanjing University of Science and Technology, China, in 2021. He is currently working as an engineer with the Southwest Technology and Engineering Research Institute. His current research interests focus on computer vision, signal processing, and target identification. E-mail: qinchaoxuan1991@163.com||GU Xiaohui was born in 1964. He received his Ph.D. degree from the School of Mechanical Engineering, Nanjing University of Science and Technology, China in 2002. He is a professor and a doctoral supervisor at the School of Mechanical Engineering, Nanjing University of Science and Technology, China. His research interests include computer vision, artificial intelligence, and reliability engineering. E-mail: gxiaohui@njust.edu.cn
Supported by:
This work was supported by the National Defense Technology Advance Research Project of China (004040204).

摘要/Abstract

Abstract:

Outdoor haze has adverse impact on outdoor image quality, including contrast loss and poor visibility. In this paper, a novel dehazing algorithm based on the decomposition strategy is proposed. It combines the advantages of the two-dimensional variational mode decomposition (2DVMD) algorithm and dark channel prior. The original hazy image is adaptively decomposed into low-frequency and high-frequency images according to the image frequency band by using the 2DVMD algorithm. The low-frequency image is dehazed by using the improved dark channel prior, and then fused with the high-frequency image. Furthermore, we optimize the atmospheric light and transmittance estimation method to obtain a defogging effect with richer details and stronger contrast. The proposed algorithm is compared with the existing advanced algorithms. Experiment results show that the proposed algorithm has better performance in comparison with the state-of-the-art algorithms.

Key words: single image dehazing, decomposition strategy, image processing, global atmospheric light

. [J]. Journal of Systems Engineering and Electronics, 2022, 33(2): 279-293.

Chaoxuan QIN, Xiaohui GU. A single image dehazing method based on decomposition strategy[J]. Journal of Systems Engineering and Electronics, 2022, 33(2): 279-293.

图/表 21

参考文献 44

1	SCHECHNER Y Y, NARASIMHAN S G, NAYAR S K. Instant dehazing of images using polarization. Proc. of the IEEE Conference on Computer Vision & Pattern Recognition, 2001. DOI: 10.1109/CVPR.2001.990493.
2	SHAO X, FEI L P, LIN W Dehazing method through polarimetric imaging and multi-scale analysis. Proc. of the SPIE Sensing Technology + Applications, 2015, 266- 273.
3	QU Y F, ZOU Z F Non-sky polarization-based dehazing algorithm for non-specular objects using polarization difference and global scene feature. Optics Express, 2017, 25 (21): 25004. doi: 10.1364/OE.25.025004
4	SHWARTZ S, NAMER E, SCHECHNER Y Y Blind haze separation. Proc. of the IEEE Computer Society Conference on Computer Vision & Pattern Recognition, 2006, 1984- 1991.
5	MIYAZAKI D, AKIYAMA D, BABA M, et al Polarization-based dehazing using two reference objects. Proc. of the IEEE International Conference on Computer Vision, 2013, 852- 859.
6	RONG Z, WANG L J Improved wavelet transform algorithm for single image dehazing. Optik-International Journal for Light and Electron Optics, 2014, 125 (13): 3064- 3066. doi: 10.1016/j.ijleo.2013.12.077
7	ZHANG H, LIU X, HUANG Z T, et al Single image dehazing based on fast wavelet transform with weighted image fusion. Proc. of the IEEE International Conference on Image Processing, 2014, 4542- 4546.
8	XIE C H, QIAO W W, ZHANG X X, et al Single image dehazing algorithm using wavelet decomposition and fast kernel regression model. Journal of Electronic Imaging, 2016, 25 (4): 043003. doi: 10.1117/1.JEI.25.4.043003
9	XIAO C X, GAN J J Fast image dehazing using guided joint bilateral filter. Visual Computer, 2012, 28 (6/8): 713- 721.
10	SERIKAWA S, LU H M Underwater image dehazing using joint trilateral filter. Computers & Electrical Engineering, 2014, 40 (1): 41- 50.
11	SUN K, WANG B, ZHENG Z Z, et al. Fast single image dehazing using iterative bilateral filter. Proc. of the International Conference on Information Engineering & Computer Science, 2010. DOI: 10.1109/ICIECS.2010.5678374.
12	SHRIVASTAVA A, JAIN S Single image dehazing based on one dimensional linear filtering and adoptive histogram equalization method. Proc. of the International Conference on Electrical, Electronics, and Optimization Techniques, 2016, 4074- 4078.
13	GALDRAN A, ALVAREZ A, BRIA A, et al On the duality between Retinex and image dehazing. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, 8212- 8221.
14	XIE B, FAN G, CAI Z X Improved single image dehazing using dark channel prior and multi-scale Retinex. Proc. of the International Conference on Intelligent System Design and Engineering Application, 2010, 848- 851.
15	ZHOU J J, ZHOU F G Single image dehazing motivated by Retinex theory. Proc. of the 2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation, 2013, 243- 247.
16	FATTAL R. Single image dehazing. ACM Transactions on Graphics, 2008, 27(3): 1–9.
17	TAN R T. Visibility in bad weather from a single image. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2008. DOI: 10.1109/CVPR.2008.4587643.
18	HE K M, SUN J, TANG X O Single image haze removal using dark channel prior. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2011, 33 (12): 2341- 2353. doi: 10.1109/TPAMI.2010.168
19	HE K M, SUN J, TANG X. Guided image filtering. Proc. of the European Conference on Computer Vision, 2010. DOI:10.1007/978-3-642-15549-9_1.
20	TAREL J, HAUTIERE N Fast visibility restoration from a single color or gray level image. Proc. of the IEEE 12th International Conference on Computer Vision, 2009, 2201- 2208.
21	WANG J B, HE N, ZHANG L L, et al Single image dehazing with a physical model and dark channel prior. Neurocomputing, 2015, 149, 718- 728. doi: 10.1016/j.neucom.2014.08.005
22	HUANG C Q, YANG D, ZHANG R L, et al Improved algorithm for image haze removal based on dark channel priority. Computers & Electrical Engineering, 2018, 70, 659- 673.
23	PENG Y T, CAO K M, COSMAN P C Generalization of the dark channel prior for single image restoration. IEEE Trans. on Image Processing, 2018, 27 (6): 2856- 2868. doi: 10.1109/TIP.2018.2813092
24	WANG Z, HOU G J, PAN Z K, et al Single image dehazing and denoising combining dark channel prior and variational models. IET Computer Vision, 2018, 12 (4): 393- 402. doi: 10.1049/iet-cvi.2017.0318
25	SUAREZ P L, SAPPA A D, VINTIMILLA B X, et al Deep learning based single image dehazing. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018, 1169- 1176.
26	SANTRA S, MONDAL R, CHANDA B Learning a patch quality comparator for single image dehazing. IEEE Trans. on Image Processing, 2018, 27 (9): 4598- 4607. doi: 10.1109/TIP.2018.2841198
27	CAI B L, XU X M, JIA K, et al Dehazenet: an end-to-end system for single image haze removal. IEEE Trans. on Image Processing, 2016, 25 (11): 5187- 5198. doi: 10.1109/TIP.2016.2598681
28	REN W Q, LIU S, ZHANG H, et al Single image dehazing via multi-scale convolutional neural networks. Proc. of the European Conference on Computer Vision, 2016, 154- 169.
29	LI B Y, PENG X L, WANG Z Y, et al Aod-net: all-in-one dehazing network. Proc. of the IEEE International Conference on Computer Vision, 2017, 4770- 4778.
30	DRAGOMIRETSKIY K, ZOSSO D Two-dimensional variational mode decomposition. Journal of Mathematical Imaging and Vision, 2017, 58 (2): 294- 320. doi: 10.1007/s10851-017-0710-z
31	MENG G F, WANG Y, DUAN J Y, et al Efficient image dehazing with boundary constraint and contextual regularization. Proc. of the International Conference on Computer Vision, 2013, 617- 624.
32	LIU C X, SHEN Y Y, SHAO Y Q, et al Sky detection- and texture smoothing-based high-visibility haze removal from images and videos. Computer Animation and Virtual Worlds, 2017, 28 (3/4): e1776.
33	SUN T, ZHU X J, PAN J S, et al No-reference image quality assessment in spatial domain. Advances in Intelligent Systems and Computing, 2015, 381- 388.
34	LIU X, ZHANG H, CHEUNG Y M, et al Efficient single image dehazing and denoising: an efficient multi-scale correlated wavelet approach. Computer Vision and Image Understanding, 2017, 162, 23- 33. doi: 10.1016/j.cviu.2017.08.002
35	XU Z, YANG X T, LI X, et al. The effectiveness of instance normalization: a strong baseline for single image dehazing. https://arxiv.org/abs/1805.03305.
36	GALDRAN A image dehazing by artificial multiple-exposure image fusion. Signal Processing, 2018, 149, 135- 147. doi: 10.1016/j.sigpro.2018.03.008
37	KIM S E, PARK T H, EOM I K Fast single image dehazing using saturation based transmission map estimation. IEEE Trans. on Image Processing, 2020, 29, 1985- 1998. doi: 10.1109/TIP.2019.2948279
38	AMER K O, ELBOUZ M, ALFALOU A, et al Enhancing underwater optical imaging by using a low-pass polarization filter. Optics Express, 2019, 27 (2): 621- 643. doi: 10.1364/OE.27.000621
39	BORKAR K, MUKHERJEE S Single image dehazing by approximating and eliminating the additional airlight component. Neurocomputing, 2020, 400, 294- 308. doi: 10.1016/j.neucom.2020.03.027
40	DHARA S K, ROY M, SEN D, et al Color cast dependent image dehazing via adaptive airlight refinement and non-linear color balancing. IEEE Trans. on Circuits and Systems for Video Technology, 2020, 31 (5): 2076- 2081.
41	RAIKWAR S C, TAPASWI S Lower bound on transmission using non-linear bounding function in single image dehazing. IEEE Trans. on Image Processing, 2020, 29, 4832- 4847. doi: 10.1109/TIP.2020.2975909
42	KANSAL I, KASANA S S Improved color attenuation prior based image de-fogging technique. Multimedia Tools and Applications, 2020, 79 (17/18): 12069- 12091.
43	HAJJAMI J, NAPOLEON T, ALFALOU A Efficient sky dehazing by atmospheric light fusion. Sensors, 2020, 20 (17): 4893. doi: 10.3390/s20174893
44	ANCUTI C O, ANCUTI C, TIMOFTE R, et al O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images: NTIRE. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018, 754- 762.

Algorithm	PSNR	SSIM	Brisque	Entropy	Running time/s
MSCWA	17.41	0.8112	22.53	6.93	1.73
DFIN	19.32	0.9052	10.12	7.07	3.11
AME	20.18	0.9034	17.5	7.12	2.14
SBTME	23.21	0.901	10.98	7.53	4.30
LPPF	20.12	0.8918	19.2	7.41	1.17
AEAC	20.86	0.8945	15.3	7.26	1.35
ARNCB	20.52	0.8237	15.8	7.17	0.91
LBBF	22.23	0.9009	10.87	7.49	1.86
ICAP	20.17	0.88125	14.2	7.19	0.99
ALF	18.64	0.7938	20.1	6.98	1.22
Proposed algorithm	23.24	0.917	10.13	7.62	0.93

A single image dehazing method based on decomposition strategy

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 21

参考文献 44

相关文章 0

编辑推荐

Metrics

本文评价