基于图像天空区域分割的去雾算法

doi:10.12305/j.issn.1001-506X.2023.06.03

系统工程与电子技术 ›› 2023, Vol. 45 ›› Issue (6): 1606-1615.doi: 10.12305/j.issn.1001-506X.2023.06.03

• 电子技术 • 上一篇

基于图像天空区域分割的去雾算法

孙景荣¹^,², 陈哲哲¹, 谢林昌¹, 杜梦欣¹, 宋诗斌³^,*

1. 西安电子科技大学空间科学与技术学院, 陕西西安 710071
2. 近地面探测技术重点实验室, 江苏无锡 214000
3. 山东科技大学机器人与智能技术重点实验室, 山东青岛 266590

收稿日期:2022-01-24 出版日期:2023-05-25 发布日期:2023-06-01
通讯作者: 宋诗斌
作者简介:孙景荣(1975—), 女, 副教授, 硕士研究生导师, 博士, 主要研究方向为低照度图像处理与分析、信号检测与信息处理
陈哲哲(1997—), 男, 硕士研究生, 主要研究方向为图像处理、计算机视觉
谢林昌(1994—), 男, 硕士研究生, 主要研究方向为计算机视觉
杜梦欣(1998—), 女, 硕士研究生, 主要研究方向为智能交通系统研究
宋诗斌(1988—), 男, 讲师, 博士, 主要研究方向为智能机器人技术、机器人定位导航

Haze removal algorithm based on image sky region segmentation

Jingrong SUN¹^,², Zhezhe CHEN¹, Linchang XIE¹, Mengxin DU¹, Shibin SONG³^,*

1. School of Aerospace Science and Technology, Xidian University, Xi'an 710071, China
2. Science and Technology on Near-Surface Defection Laboratory, Wuxi 214000, China
3. Shandong Provincial Key Laboratory of Robot and Intelligent Technology, Shandong University of Science and Technology, Qingdao 266590, China

Received:2022-01-24 Online:2023-05-25 Published:2023-06-01
Contact: Shibin SONG

摘要/Abstract

摘要：

为了提升图像去雾效果, 提出了基于天空区域分割的透射率合成图像去雾算法, 通过雾霾图像构造的概率分布函数, 结合迭代阈值分割及天空区域的暗、亮通道以及最大连通性确定出粗分割阈值。利用引导滤波加强天空与非天空区域像素灰度的差异性，实现了精准分割。利用对数自适应变换估计了天空区域透射率, 利用改进的暗通道先验算法估计了非天空区域透射率, 通过合成对应像素的透射率实现了图像的去雾。实验结果表明, 相比其他去雾算法, 所提算法在各客观指标上均有所提高, 对天空与非天空区域分割准确, 去雾图像整体视觉效果良好。

关键词: 天空分割, 图像去雾, 暗通道先验, 透射率映射

Abstract:

In order to improve the haze removal effect of images, an image haze removal algorithm based on transmissivity synthesis of sky region segmentation is proposed in this paper. The rough segmentation threshold is determined based on the probability distribution function constructed by haze image with the combination of iterative threshold segmentation with dark and bright channels and the maximum connectivity. Guided filtering is used to enhance the difference of the pixel gray between sky and non-sky regions to achieve the accurate segmentation. Logarithmic adaptive transformation is adopted to estimate the transmissivity in sky region, and the improved dark channel prior algorithm is used to estimate the transmissivity in non-sky region. The image was defogged by synthesizing the transmissivity of the corresponding pixels. Experimental results show that compared with other defogging algorithms, the algorithm presented in this paper achieves improvements in all objective indexes, which accurately segments sky and non-sky regions, and achieves good overall visual effect of defogging images.

Key words: sky segmentation, image defogging, dark channel prior, transmittance mapping

中图分类号:

TP391.41

孙景荣, 陈哲哲, 谢林昌, 杜梦欣, 宋诗斌. 基于图像天空区域分割的去雾算法[J]. 系统工程与电子技术, 2023, 45(6): 1606-1615.

Jingrong SUN, Zhezhe CHEN, Linchang XIE, Mengxin DU, Shibin SONG. Haze removal algorithm based on image sky region segmentation[J]. Systems Engineering and Electronics, 2023, 45(6): 1606-1615.

图/表 11

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

参考文献 33

1	THEPADE S D, NAWALE C M, SURYAVANSHI M V, et al. Single image dehazing using a weighted fusion of dark and bright channel prior with gamma correction[C]//Proc. of the 2nd International Conference for Emerging Technology, 2021.
2	王柯俨, 胡妍, 王怀, 等. 结合天空分割和超像素级暗通道的图像去雾算法[J]. 吉林大学学报(工学版), 2019, 49 (4): 1377- 1384. doi: 10.13229/j.cnki.jdxbgxb20180208
	WANG K Y , HU Y , WANG H , et al. Image defogging algorithm based on sky segmentation and super-pixel dark channel[J]. Journal of Jilin University (Engineering and Technology Edition), 2019, 49 (4): 1377- 1384. doi: 10.13229/j.cnki.jdxbgxb20180208
3	黄富瑜, 李刚, 邹昌帆, 等. 暗原色先验自适应图像去雾方法[J]. 光电子·激光, 2019, 30 (12): 1323- 1330. doi: 10.16136/j.joel.2019.12.0271
	HUANG F Y , LI G , ZOU C F , et al. Dark priori adaptive image defogging method[J]. Journal of optoelectronics laser, 2019, 30 (12): 1323- 1330. doi: 10.16136/j.joel.2019.12.0271
4	HE K M , SUN J , TANG X O , et al. Single image haze removal using dark channel prior[J]. IEEE Trans.on Pattern Analysis & Machine Intelligence, 2011, 33 (12): 2341- 2353.
5	MENG G F , WANG Y , DUAN J Y . Efficient image dehazing with boundary constraint and contextual regularization[J]. Proc.of the IEEE International Conference on Computer Vision, 2013, 34 (12): 617- 624.
6	BERMAN D, TREIBITZ T, AVIDAN S. Non-local image dehazing[C]//Proc. of the IEEE Conference on Computer Vision & Pattern Recognition, 2016: 1674-1682.
7	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, 2019, 43 (5): 592- 599. doi: 10.14177/j.cnki.32-1397n.2019.43.05.008
	PAN J H , GAO Y . Image restoration algorithm based on sky region segmentation and multi-scale fusion[J]. Journal of Nanjing University of Science and Technology, 2019, 43 (5): 592- 599. doi: 10.14177/j.cnki.32-1397n.2019.43.05.008
8	MEI W, LI X. Single image dehazing using dark channel fusion and haze density weight[C]//Proc. of the IEEE 9th International Conference on Electronics Information and Emergency Communication, 2019: 579-585.
9	NARASIMHAN S G , NAYAR S K . Contrast restoration of weather degraded images[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2003, 25 (6): 713- 724. doi: 10.1109/TPAMI.2003.1201821
10	李熙莹, 朱肯钢. 结合天空分割和局部透射率优化交通图像去雾算法[J]. 计算机与现代化, 2019, 4 (5): 51- 58. doi: 10.3969/j.issn.1006-2475.2019.05.010
	LI X Y , ZHU K G . Optimization of fog removal algorithm for traffic image based on sky segmentation and local transmittance[J]. Computer & Modernization, 2019, 4 (5): 51- 58. doi: 10.3969/j.issn.1006-2475.2019.05.010
11	HE K M , SUN J , TANG X O . Guided image filtering[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2013, 35 (6): 1397- 1409. doi: 10.1109/TPAMI.2012.213
12	WANG W C , YUAN X H , WU X J , et al. Fast image dehazing method based on linear transformation[J]. IEEE Trans.on Multimedia, 2017, 19 (6): 1142- 1155. doi: 10.1109/TMM.2017.2652069
13	暴婉婷, 王俊平, 魏书蕾, 等. 天空区域分割修正的图像去雾新算法[J]. 西安电子科技大学学报, 2019, 46 (2): 164- 169.
	BAO W T , WANG J P , WEI S L , et al. A new algorithm for image haze removal based on sky region segmentation[J]. Journal of Xidian University, 2019, 46 (2): 164- 169.
14	LI W X , JIE W , MAHMOUD Z S . Single image dehazing algorithm based on sky region segmentation[J]. Lecture Notes in Computer Science, 2021, 8 (3): 489- 500.
15	LIU Y , LI H J , WANG M H . Single image dehazing via large sky region segmentation and multi-scale opening dark channel model[J]. IEEE Access, 2017, 5, 8890- 8903. doi: 10.1109/ACCESS.2017.2710305
16	李树平, 张辽, 刘俊利. 基于天空区域分割和条件约束优化的图像去雾研究[J]. 河南理工大学学报(自然科学版), 2021, 40 (5): 132- 138.
	LI S P , ZHANG L , LIU J L . Image defogging based on sky region segmentation and conditional optimization[J]. Journal of Henan Polytechnic University (Natural Science Edition), 2021, 40 (5): 132- 138.
17	YANG S , SUN Z Y , JIANG Q , et al. A mixed transmission estimation iterative method for single image dehazing[J]. IEEE Access, 2021, 9 (1): 63685- 63699.
18	JACKSON J, ARIYO O, ACHEAMPONG K, et al. Hybrid single image dehazing with bright channel and dark channel priors[C]//Proc. of the 2nd International Conference on Image, Vision and Computing, 2017: 381-385.
19	ZHANG L B , WANG S , WANG X H . Single image dehazing based on bright channel prior model and saliency analysis stra-tegy[J]. IET Image Processing, 2021, 15 (5): 1023- 1031.
20	CUI T, QU L Q, TIAN J D, et al. Single image haze removal based on luminance weight prior[C]//Proc. of the IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, 2016: 332-336.
21	TANG H Q, LI Z, ZHONG H B, et al. Sky-preserved image dehazing and enhancement for outdoor scenes[C]//Proc. of the IEEE 4th International Conference on Electronics Technology, 2021: 1266-1271.
22	SALAZAR-COLORES S , MOYA-SANCHEZ E U , ARRE-GUIN J M R , et al. Fast single image defogging with robust sky detection[J]. IEEE Access, 2020, 8, 149176- 149189.
23	JIANG Z Y , SUN X D , WANG X C , et al. Image defogging algorithm based on sky region segmentation and dark channel prior[J]. Journal of Systems Science and Information, 2020, 8 (5): 92- 102.
24	BI G L , REN J Y , FU T J , et al. Image dehazing based on accurate estimation of transmission in the atmospheric scattering model[J]. IEEE Photonics Journal, 2017, 9 (4): 797629.
25	杨燕, 张浩文, 张金龙. 结合天空分割和透射率映射的图像去雾[J]. 光学精密工程, 2021, 29 (2): 400- 410.
	YANG Y , ZHANG H W , ZHANG J L . Image fog removal based on sky segmentation and transmittance mapping[J]. Optics and Precision Engineering, 2021, 29 (2): 400- 410.
26	XIE B, YANG J X, SHEN J H, et al. Image defogging method combining light field depth estimation and dark channel[C]//Proc. of the IEEE International Conference on Consumer Electronics and Computer Engineering, 2021: 745-749.
27	WANG W C , CHANG F L , JI T , et al. A fast single-image dehazing method based on a physical model and gray projection[J]. IEEE Access, 2018, 6, 5641- 5653.
28	JACKSON J , SHE K , AGYEKUM K O , et al. A fast single-image dehazing algorithm based on dark channel prior and rayleigh scattering[J]. IEEE Access, 2020, 2 (8): 73330- 73339.
29	ZHANG J , TAO D . FAMED-Net: a fast and accurate multi-scale end-to-end dehazing network[J]. IEEE Trans.on Image Processing, 2019, 72- 84.
30	孙景荣, 谢林昌, 杜梦欣, 等. 一种非线性变换的自适应透射率去雾算法[J]. 西安电子科技大学报, 2022, 49 (1): 208- 215.
	SUN J R , XIE L C , DU M X , et al. An adaptive transmittance defogging algorithm based on nonlinear transformation[J]. Journal of Xidian University, 2022, 49 (1): 208- 215.
31	CHENG Z H, XIN X, SHEN Y C. A novel image defogging algorithm based on multi-resolution fusion transform[C]//Proc. of the IEEE 2nd International Conference on Opto-Electronic Information Processing, 2017: 45-48.
32	ZHU Q S , MAI J M , SHAO L . A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Trans.on Image Processing, 2015, 24 (11): 3522- 3533.
33	DONG H, PAN J S, XIANG L, et al. Multi-scale boosted dehazing network with dense feature fusion[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 2154-2164.

参数	去雾算法
参数	He算法	Meng算法	Berman算法	潘健鸿算法	Mei算法	本文算法
平均耗时	12.240 1	7.762 4	5.634 1	6.214 6	3.906 4	4.164 5

[1]	梅葳, 李昕. 基于重构暗通道的二次正弦衰减的去雾算法[J]. 系统工程与电子技术, 2021, 43(5): 1169-1175.
[2]	眭萍, 毕笃彦, 马时平, 何林远. 基于局部一致性的马尔可夫随机场去雾[J]. 系统工程与电子技术, 2017, 39(5): 1154-1159.
[3]	曲晨, 毕笃彦, 严盛文, 何林远. 基于明暗像素先验的随机游走图像去雾[J]. 系统工程与电子技术, 2017, 39(10): 2368-2375.

基于图像天空区域分割的去雾算法

Haze removal algorithm based on image sky region segmentation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 33

相关文章 3

编辑推荐

Metrics

本文评价