基于显著性权重的多曝光融合的单幅雾天图像复原算法

李红云; 施云; 高银

doi:10.11999/JEIT200931

基于显著性权重的多曝光融合的单幅雾天图像复原算法

doi: 10.11999/JEIT200931

李红云¹,
施云¹,
高银^2, ,

1.
泉州职业技术大学晋江 362200
2.
泉州装备制造研究所晋江 362200

基金项目: 国家自然科学基金(62001452)，福建省中青年教师教育科研(JAT191675)，泉州市科技计划 (2020C054, 2019C009R)

详细信息

作者简介:
李红云：女，1982年生，讲师，研究方向为室内定位地图构建和视频图像复原

施云：男，1990年生，讲师，研究方向为图像处理与机器人自适应控制

高银：男，1985年生，高级工程师，研究方向为图像增强、平滑、融合和复原

通讯作者:
高银　yngaoyin@163.com

中图分类号: TN911.73; TP391
计量
- 文章访问数: 956
- HTML全文浏览量: 440
- PDF下载量: 122
- 被引次数: 0
出版历程
- 收稿日期: 2020-10-30
- 修回日期: 2021-04-20
- 网络出版日期: 2021-08-18
- 刊出日期: 2022-01-10

Single Image Dehazing via Saliency Weighted Multi-exposure Fusion

LI Hongyun¹,
SHI Yun¹,
GAO Yin^{2
, ,}

1.
Quanzhou Vocational and Technical University, Jinjiang 362200, China
2.
Quanzhou Institute of Equipment Manufacturing, Jinjiang 362200, China

Funds: The National Natural Science Foundation of China (62001452), The Fujian Province Young band Middle-aged Teacher Education Research Project(JAT191675), The Science and Technology Program of Quanzhou (2020C054, 2019C009R)

摘要

摘要: 传统暗原色理论的相关算法，在处理雾天图像时会产生颜色的畸变和亮度的损失，针对该情况，该文提出基于权重多曝光融合的单幅雾天图像复原算法。首先通过雾天图像的直方图分析，获取全局大气背景光值的区域。其次构造一种新的Kirsh算子的高阶差分滤波方法，优化透射率图像。最后设计一种基于显著性权重的多曝光图像融合方法，提高处理后图像的视觉效果。该文采用自然图像和合成图像进行实验，与多种算法通过主观和客观评价，表明该文算法比现有的算法有更高的复原效果。
- 图像去雾 /
- 自适应边界限制 /
- 高阶差分滤波 /
- 显著性多曝光融合
Abstract: Previous techniques are not sufficient enough to deal with dehazing problems by using various hand-crafted priors and appear image hue and brightness distortion. In this paper, a saliency weighted multi-exposure fusion is proposed for single image dehazing. To produce several images with different exposures, a novel segmentation method is exploited to capture the range of global atmospheric light approximately, and a new Kirsh high-order difference filtering method is employed to optimize the transmission map. A saliency weighted multi-exposure fusion method is constructed to improve the dehazing quality. Extensive experimental results on both subjective and objective evaluation demonstrate that the proposed algorithm performs favorably against the state-of-the-art algorithms.
- Image dehazing /
- Adaptive boundary constraint /
- High order difference filtering /
- Saliency weighted multi-exposure fusion

HTML全文

图 1 算法的流程图

下载: 全尺寸图片幻灯片

图 2 区域分割的对比图

下载: 全尺寸图片幻灯片

图 3 显著性多曝光融合过程

下载: 全尺寸图片幻灯片

图 4 滤波后透射率图像的对比

下载: 全尺寸图片幻灯片

图 5 自然图像去雾对比图

下载: 全尺寸图片幻灯片

图 6 合成图像去雾对比图

下载: 全尺寸图片幻灯片

表 1 自然图像中不同方法的客观评价分析

	工地	寺庙	稻田	原野
I/E	27.16/0.24	24.02/0.12	34.55/0.01	28.74/-0.12
文献[10]	26.16/0.17	20.34/0.07	31.64/0.03	26.85/-0.14
文献[16]	22.71/0.13	17.98/0.11	29.60/0.03	25.44/0.06
文献[28]	23.99/0.13	18.99/0.09	26.02/0.11	26.01/0.02
文献[29]	21.46/0.14	18.46/0.11	27.00/0.33	27.32/0.01
文献[30]	25.96/0.18	18.43/0.11	26.10/0.06	24.87/0.09
文献[31]	26.23/0.16	18.29/0.11	35.14/0.05	32.56/-0.01
本文	21.51/0.24	17.31/0.16	28.93/0.27	25.13/0.25

下载: 导出CSV

表 2 合成图像中不同方法的客观评价分析

	校园	小区	马路	宫殿
P/R	–/–	–/–	–/–	–/–
文献[10]	14.93/0.62	15.30/0.51	12.18/0.46	16.36/0.53
文献[16]	20.79/0.68	16.49/0.53	13.99/0.55	16.58/0.55
文献[28]	15.64/0.61	13.66/0.52	14.49/0.53	18.93/0.55
文献[29]	22.70/0.67	19.82/0.58	13.67/0.53	19.32/0.56
文献[30]	23.44/0.69	16.63/0.53	19.31/0.54	18.84/0.54
文献[31]	19.49/0.55	13.31/0.47	11.57/0.41	14.59/0.47
our	24.04/0.74	22.16/0.64	23.53/0.61	23.02/0.57

下载: 导出CSV

表 3 各种算法的处理时间对比(s)

方法	文献[10]	文献[16]	文献[28]	文献[29]	文献[30]	文献[31]	本文
工地	40.72	5.82	56.36	3.74	16.71	1.64	12.61
寺庙	29.32	5.42	40.06	2.46	12.33	1.54	11.53
稻田	13.54	4.31	22.25	1.52	11.70	1.46	9.58
原野	18.52	4.64	25.72	1.88	12.04	1.43	12.04

下载: 导出CSV

参考文献(35)

[1]	FREI W. Image enhancement by histogram hyperbolization[J]. Computer Graphics and Image Processing, 1977, 6(3): 286–294. doi: 10.1016/S0146-664X(77)80030-0
[2]	PIZER S M, AMBURN E P, AUSTIN J D, et al. Adaptive histogram equalization and its variations[J]. Computer Vision, Graphics, and Image Processing, 1987, 39(3): 355–368. doi: 10.1016/S0734-189X(87)80186-X
[3]	JOBSON D J, RAHMAN Z, and WOODELL G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing, 1997, 6(7): 965–976. doi: 10.1109/83.597272
[4]	LAND E H. The retinex theory of color vision[J]. Scientific American, 1977, 237(6): 108–128. doi: 10.1038/scientificamerican1277-108
[5]	JOBSON D J, RAHMAN Z, and WOODELL G A. Properties and performance of a center/surround retinex[J]. IEEE Transactions on Image Processing, 1997, 6(3): 451–462. doi: 10.1109/83.557356
[6]	NAYAR S K and NARASIMHAN S G. Vision in bad weather[C]. The Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, 1999: 820–827. doi: 10.1109/ICCV.1999.790306.
[7]	SCHECHNER Y Y, NARASIMHAN S G, and NAYAR S K. Instant dehazing of images using polarization[C]. The 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, USA, 2001. doi: 10.1109/CVPR.2001.990493.
[8]	FATTAL R. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3): 1–9. doi: 10.1145/1360612.1360671
[9]	FATTAL R. Dehazing using color-lines[J]. ACM Transactions on Graphics, 2014, 34(1): 13. doi: 10.1145/2651362
[10]	HE Kaiming, SUN Jian, and TANG Xiaoou. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341–2353. doi: 10.1109/TPAMI.2010.168
[11]	高银, 云利军, 石俊生, 等. 基于各向异性高斯滤波的暗原色理论雾天彩色图像增强算法[J]. 计算机辅助设计与图形学学报, 2015, 27(9): 1701–1706. doi: 10.3969/j.issn.1003-9775.2015.09.014 GAO Yin, YUN Lijun, SHI Junsheng, et al. Enhancement dark channel algorithm of color fog image based on the anisotropic Gaussian filtering[J]. Journal of Computer-Aided Design &Computer Graphics, 2015, 27(9): 1701–1706. doi: 10.3969/j.issn.1003-9775.2015.09.014
[12]	GAO Yin, SU Yijing, LI Qiming, et al. Single fog image restoration with multi-focus image fusion[J]. Journal of Visual Communication and Image Representation, 2018, 55: 586–595. doi: 10.1016/j.jvcir.2018.07.004
[13]	HUANG S C, YE Jianhui, and CHEN Bohan. An advanced single-image visibility restoration algorithm for real-world hazy scenes[J]. IEEE Transactions on Industrial Electronics, 2015, 62(5): 2962–2972. doi: 10.1109/TIE.2014.2364798
[14]	XIAO Chunxia and GAN Jiajia. Fast image dehazing using guided joint bilateral filter[J]. The Visual Computer, 2012, 28(6/8): 713–721. doi: 10.1007/s00371-012-0679-y
[15]	HE Kaiming, SUN Jian, and TANG Xiaoou. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397–1409. doi: 10.1109/TPAMI.2012.213
[16]	MENG Gaofeng, WANG Ying, DUAN Jianyong, et al. Efficient image dehazing with boundary constraint and contextual regularization[C]. The 2013 IEEE International Conference on Computer Vision, Sydney, Australia, 2013: 617–624. doi: 10.1109/ICCV.2013.82.
[17]	ZHU Qingsong, MAI Jiaming, and SHAO Ling. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Transactions on Image Processing, 2015, 24(11): 3522–3533. doi: 10.1109/TIP.2015.2446191
[18]	TANG Ketan, YANG Jianchao, and WANG Jue. Investigating haze-relevant features in a learning framework for image dehazing[C]. The 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 2995–3002. doi: 10.1109/CVPR.2014.383.
[19]	CAI Bolun, XU Xiangmin, JIA Kui, et al. Dehazenet: An end-to-end system for single image haze removal[J]. IEEE Transactions on Image Processing, 2016, 25(11): 5187–5198. doi: 10.1109/TIP.2016.2598681
[20]	REN Wenqi, PAN Jinshan, ZHANG Hua, et al. Single image dehazing via multi-scale convolutional neural networks with holistic edges[J]. International Journal of Computer Vision, 2020, 128(1): 240–259. doi: 10.1007/s11263-019-01235-8
[21]	ZHANG He and PATEL V M. Densely connected pyramid dehazing network[C]. The 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 3194–3203. doi: 10.1109/CVPR.2018.00337.
[22]	ZHANG He, SINDAGI V, and PATEL V M. Multi-scale single image dehazing using perceptual pyramid deep network[C]. The 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, USA, 2018: 1015–1024. doi: 10.1109/CVPRW.2018.00135.
[23]	WANG Anna, WANG Wenhui, LIU Jinglu, et al. Aipnet: Image-to-image single image dehazing with atmospheric illumination prior[J]. IEEE Transactions on Image Processing, 2019, 28(1): 381–393. doi: 10.1109/TIP.2018.2868567
[24]	ANCUTI C O and ANCUTI C. Single image dehazing by multi-scale fusion[J]. IEEE Transactions on Image Processing, 2013, 22(8): 3271–3282. doi: 10.1109/TIP.2013.2262284
[25]	GALDRAN A, VAZQUEZ-CORRAL J, PARDO D, et al. Fusion-based variational image dehazing[J]. IEEE Signal Processing Letters, 2017, 24(2): 151–155. doi: 10.1109/LSP.2016.2643168
[26]	GAO Yin, SU Yijing, LI Qiming, et al. Single image dehazing via self-constructing image fusion[J]. Signal Processing, 2020, 167: 107284. doi: 10.1016/j.sigpro.2019.107284
[27]	XU Zhiyuan, LIU Xiaoming, and CHEN Xiaonan. Fog removal from video sequences using contrast limited adaptive histogram equalization[C]. 2009 International Conference on Computational Intelligence and Software Engineering, Wuhan, China, 2009: 1–4. doi: 10.1109/CISE.2009.5366207.
[28]	SULAMI M, GLATZER I, FATTAL R, et al. Automatic recovery of the atmospheric light in hazy images[C]. IEEE International Conference on Computational Photography (ICCP), Santa Clara, USA, 2014: 1–11. doi: 10.1109/ICCPHOT.2014.6831817.
[29]	BERMAN D, TREIBITZ T, and AVIDAN S. Non-local image dehazing[C]. The 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 1674–1682. doi: 10.1109/CVPR.2016.185.
[30]	ZHANG Shengdong, HE Fazhi, and YAO Jian. Single image dehazing using deep convolution neural networks[C]. 18th Pacific-Rim Conference on Multimedia, Harbin, China, 2017: 128–137. doi: 10.1007/978-3-319-77380-3_13.
[31]	BUI T M and KIM W. Single image dehazing using color ellipsoid prior[J]. IEEE Transactions on Image Processing, 2018, 27(2): 999–1009. doi: 10.1109/TIP.2017.2771158
[32]	LI Boyi, REN Wenqi, FU Dengpan, et al. Benchmarking single-image dehazing and beyond[J]. IEEE Transactions on Image Processing, 2019, 28(1): 492–505. doi: 10.1109/TIP.2018.2867951
[33]	ZHANG Lin, ZHANG Lei, and BOVIK A C. A feature-enriched completely blind image quality evaluator[J]. IEEE Transactions on Image Processing, 2015, 24(8): 2579–2591. doi: 10.1109/TIP.2015.2426416
[34]	CHEN Xiaoqiao, ZHANG Qingyi, LIN Manhui, et al. No-reference color image quality assessment: From entropy to perceptual quality[J]. EURASIP Journal on Image and Video Processing, 2019, 2019(1): 77. doi: 10.1186/s13640-019-0479-7
[35]	YANG Guangyi, LI Deshi, LU Fan, et al. RVSIM: A feature similarity method for full-reference image quality assessment[J]. EURASIP Journal on Image and Video Processing, 2018, 2018(1): 6. doi: 10.1186/s13640-018-0246-1