水下光学图像处理研究进展

郭银景; 吴琪; 苑娇娇; 侯佳辰; 吕文红

doi:10.11999/JEIT190803

水下光学图像处理研究进展

doi: 10.11999/JEIT190803

郭银景^{1, 3, ,},
吴琪¹,
苑娇娇¹,
侯佳辰¹,
吕文红^{2, 3}

1.
山东科技大学电子信息工程学院青岛 266590
2.
山东科技大学交通学院青岛 266590
3.
青岛智海牧洋有限公司青岛 266590

基金项目: 国家自然科学基金(61471224)，山东省重点研发计划(公益类专项)项目(2018GHY115022)

详细信息

作者简介:
郭银景：男，1966年生，教授，研究方向为无线通信、图像信息处理、AUV导航与控制等

吴琪：女，1997年生，硕士生，研究方向为信号与信息处理

苑娇娇：女，1996年生，硕士生，研究方向为通信与信息系统

侯佳辰：女，1998年生，硕士生，研究方向为电子与通信工程

吕文红：女，1968年生，教授，研究方向为导航与通信系统、运筹学与最优化方法等

通讯作者:
郭银景　gyjlwh@163.com

中图分类号: TN911.73; TP391
计量
- 文章访问数: 2570
- HTML全文浏览量: 1613
- PDF下载量: 495
- 被引次数: 0
出版历程
- 收稿日期: 2019-10-16
- 修回日期: 2020-02-28
- 网络出版日期: 2020-12-11
- 刊出日期: 2021-02-23

Research Progress on Underwater Optical Image Processing

Yinjing GUO^{1, 3
, ,},
Qi WU¹,
Jiaojiao YUAN¹,
Jiachen HOU¹,
Wenhong LÜ^{2, 3}

1.
College of Electronic Information Engineering, Shandong University of Science and Technology, Qingdao 266590, China
2.
College of Transportation, Shandong University of Science and Technology, Qingdao 266590, China
3.
Qingdao Intelligent Ocean Technology Co, Qingdao 266590, China

Funds: The National Natural Science Foundation of China (61471224), Shandong Province Key Research and Development Program (Special Project for Public Welfare) (2018GHY115022)

摘要

摘要:
水下光学图像处理是水下设备完成深海探测和作业任务的重要依据。在简述了水下光学图像处理的研究背景、意义及其研究热点的基础上，该文从水下图像光照因素改善与颜色校正两个方面，详细综述了水下成像技术和水下图像清晰化算法的研究进展，重点论述了基于成像模型的图像复原方法和图像增强方法两个最为活跃的研究方向的研究现状。根据水下光学图像处理研究热点，分别从考虑光的前向折射，水下成像模型和图像增强算法结合，引入相关领域新型算法和提高图像处理实时性的角度，展望了水下光学图像处理研究的发展趋势。
- 图像处理 /
- 水下成像 /
- 图像清晰化算法 /
- 图像复原 /
- 图像增强
Abstract:
Underwater optical image processing is an important basis for underwater equipment to complete deep-sea exploration and operation tasks. Based on a brief description of the research background, significance and hotspots of underwater optical image processing, this paper gives a detailed overview of underwater imaging technology and clearness of underwater images from the aspects of improving the lighting factors and color correction of underwater images. The research progress focuses on the research status of the two most active research directions of image restoration methods and image enhancement methods based on imaging models. According to the research hotspots of underwater optical image processing, the research of underwater optical image processing is prospected from the perspectives of considering the forward refraction of light, combining underwater imaging models and image enhancement algorithms, introducing new algorithms in related fields, and improving the real-time performance of image processing.
- Image processing /
- Underwater imaging /
- Image sharpening algorithm /
- Image restoration /
- Image enhancement

HTML全文

图 1 水下光学成像原理图

下载: 全尺寸图片幻灯片

图 2 文献[17]提出的水下成像方法

下载: 全尺寸图片幻灯片

图 3 文献[21]提出的水下立体成像方法效果图

下载: 全尺寸图片幻灯片

图 4 文献[28]中方法实验效果对比图

下载: 全尺寸图片幻灯片

图 5 文献[29]与文献[30]实验结果对比

下载: 全尺寸图片幻灯片

图 6 文献[35]与文献[36]实验结果对比

下载: 全尺寸图片幻灯片

图 7 Coral清晰化对比^[45]

下载: 全尺寸图片幻灯片

表 1 文献[28]指标对比

文献[28] 指标	AG (平均梯度)	DoAG (平均梯度差值)	H (信息熵)	DoH (信息熵差值)
图4(a)	3.2504	–	6.1859	–
图4(b)	5.8932	2.6428	6.9939	0.7257
图4(c)	6.1823	2.9319	6.9939	0.8080

下载: 导出CSV

表 2 基于颜色校正的清晰化算法表

清晰化算法	算法切入角度	颜色校正处理		实验效果	文献
图像增强方法	颜色恒常理论	传统方法	图像颜色补偿	提高图像对比度细节深化	[38-42]
		传统方法	基于Retinex算法	改善模糊、亮度问题	[43-45]
		新思路	基于深度学习框架	颜色自然、色偏修正	[46]
		新思路	以视网膜为灵感	颜色自然、色偏修正	[47]
图像复原方法	蓝绿基调考量	平衡蓝绿颜色通道分量		图像远景颜色复原效果更优	[48-50]
	红通道信息考量	传统方法	颜色信息通道估计	精确估计透射率以及背景光信息，优化颜色补偿	[51-54]
	模型重建改进	新思路	神经网络方法及其深度改进	恢复图像对比及颜色投射提高模型对浊度的容忍度	[55,56]

下载: 导出CSV

表 3 各算法相关指标对比表^[45]

图像	指标	原图像	WCID 算法	Retinex 算法	结合Jaffe McGlamer 模型和Retinex算法
Coral	K	1.9882	1.3614	1.3479	1.3910
	C	29.9062	40.2765	61.0173	64.7464
	GMG	34.2907	41.0527	59.6509	65.1298

下载: 导出CSV

参考文献(58)

BONIN F, BURGUERA A, and OLIVER G. Imaging systems for advanced underwater vehicles[J]. Journal of Maritime Research, 2011, 8(1): 65–86.

SCHECHNER Y Y and KARPEL N. Clear underwater vision[C]. The 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, USA, 2004: 89–97. doi: 10.1109/CVPR.2004.1315078.

LU Huimin, LI Yujie, and SERIKAWA S. Computer Vision for Ocean Observing[M]. Artificial Intelligence and Computer Vision. Cham: Springer, 2017, 672: 1–16. doi: 10.1007/978-3-319-46245-5_1.

张莉云. 水下图像清晰化算法研究[D]. [硕士论文], 天津大学, 2017.

ZHANG Liyun. Research on visibility enhancement of underwater images[D]. [Master dissertation], Tianjin University, 2017.

冷洁. 水下光学成像系统的研究现状和展望[J]. 激光杂志, 2008, 29(1): 7–8. doi: 10.3969/j.issn.0253-2743.2008.01.003

LENG Jie. The investigation and prospect of underwater imaging system[J]. Laser Journal, 2008, 29(1): 7–8. doi: 10.3969/j.issn.0253-2743.2008.01.003

FOURNIER G R, BONNIER D, FORAND J L, et al. LUCIE ROV-mounted laser imaging system[C]. Ocean Optics XI, San Diego, USA, 1992, 1750: 443–452. doi: 10.1117/12.140673.

FOURNIER G R, BONNIER D, FORAND J L, et al. Range-gated underwater laser imaging system[J]. Optical Engineering, 1993, 32(9): 2185–2190. doi: 10.1117/12.143954

WEIDEMANN A, FOURNIER G R, FORAND L, et al. In harbor underwater threat detection/identification using active imaging[C]. Photonics for Port and Harbor Security, Orlando, USA, 2005: 59–70. doi: 10.1117/12.603601.

TAN C S, SLUZEK A, and SEET G G L. Model of gated imaging in turbid media[J]. Optical Engineering, 2005, 44(11): 116002. doi: 10.1117/1.2124567

TAN C S, SLUZEK A, SEET GL G, et al. Range gated imaging system for underwater robotic vehicle[C]. OCEANS 2006-Asia Pacific, Singapore, 2007: 1–6. doi: 10.1109/oceansap.2006.4393938.

MINOR L G. Dual mode semi-active laser/laser radar seeker[P]. US, 6262800, 2001.

JAFFE J S. Development of a laser line scan LIDAR imaging system for AUV use[R]. Award Number: N00014-09-1-0477, 2010.

CARIOU J, LE JEUNE B, LOTRIAN J, et al. Polarization effects of seawater and underwater targets[J]. Applied Optics, 1990, 29(11): 1689–1695. doi: 10.1364/ao.29.001689

曹念文, 刘文清, 张玉钧. 偏振成像技术提高成像清晰度、成像距离的定量研究[J]. 物理学报, 2000, 49(1): 61–66. doi: 10.3321/j.issn:1000-3290.2000.01.014

CAO Nianwen, LIU Wenqing, and ZHANG Yujun. Quantitative study of improvements of the imaging contrast and imaging range by the polarization technique[J]. Acta Physica Sinica, 2000, 49(1): 61–66. doi: 10.3321/j.issn:1000-3290.2000.01.014

CRONIN T W, SHASHAR N, CALDWELL R L, et al. Polarization vision and its role in biological signaling[J]. Integrative and Comparative Biology, 2003, 43(4): 549–558. doi: 10.1093/icb/43.4.549

TREIBITZ T and SCHECHNER Y Y. Active polarization descattering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(3): 385–399. doi: 10.1109/TPAMI.2008.85

SCHECHNER Y Y and AVERBUCH Y. Regularized image recovery in scattering media[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(9): 1655–1660. doi: 10.1109/tpami.2007.1141

ARNOLD-BOS A, MALKASSE J P, and KERVERN G. Towards a model-free denoising of underwater optical images[C]. Europe Oceans 2005, Brest, France, 2005: 527–532. doi: 10.1109/oceanse.2005.1511770.

TREIBITZ T and SCHECHNER Y Y. Turbid scene enhancement using multi-directional illumination fusion[J]. IEEE Transactions on Image Processing, 2012, 21(11): 4662–4667. doi: 10.1109/TIP.2012.2208978

HARDY K, CAMERON J, HERBST L, et al. Hadal landers: The DEEPSEA CHALLENGE ocean trench free vehicles[C]. 2013 OCEANS - San Diego, San Diego, USA, 2013: 1–10.

ROSER M, DUNBABIN M, and GEIGER A. Simultaneous underwater visibility assessment, enhancement and improved stereo[C]. 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China, 2014: 3840–3847. doi: 10.1109/icra.2014.6907416.

GARCIA R, NICOSEVICI T, and CUFI X. On the way to solve lighting problems in underwater imaging[C]. OCEANS’02 MTS/IEEE, Biloxi, USA, 2002: 1018–1024. doi: 10.1109/oceans.2002.1192107.

JIANG Qin, WANG Guoyu, GONG Benxing, et al. A novel approach to underwater de-scattering based on sparse and low-rank matrix decomposition[C]. OCEANS - MTS/IEEE Kobe Techno-Oceans, Kobe, Japan, 2018: 1–4. doi: 10.1109/oceanskobe.2018.85591.

PAN Panwang, YUAN Fei, and CHENG En. Underwater image de-scattering and enhancing using dehazenet and HWD[J]. Journal of Marine Science and Technology, 2018, 26(4): 531–540.

LU Huimin, LI Yujie, UEMURA T, et al. Low illumination underwater light field images reconstruction using deep convolutional neural networks[J]. Future Generation Computer Systems, 2018, 82: 142–148. doi: 10.1016/j.future.2018.01.001

LI Yujie, LU Huimin, LI K C, et al. Non-uniform de-scattering and de-blurring of underwater images[J]. Mobile Networks and Applications, 2018, 23(2): 352–362. doi: 10.1007/s11036-017-0933-7

张颢, 范新南, 李敏, 等. 基于光学成像模型的水下图像超分辨率重构[J]. 计算机与现代化, 2017(4): 7–13. doi: 10.3969/j.issn.1006-2475.2017.04.002

ZHANG Hao, FAN Xinnan, LI Min, et al. Underwater image super-resolution reconstruction based on optical imaging model[J]. Computer and Modernization, 2017(4): 7–13. doi: 10.3969/j.issn.1006-2475.2017.04.002

王鑫, 朱行成, 宁晨, 等. 融合暗原色先验和稀疏表示的水下图像复原[J]. 电子与信息学报, 2018, 40(2): 264–271. doi: 10.11999/jeit170381

WANG Xin, ZHU Xingcheng, NING Chen, et al. Combination of dark-channel prior with sparse representation for underwater image restoration[J]. Journal of Electronics &Information Technology, 2018, 40(2): 264–271. doi: 10.11999/jeit170381

PAN Panwang, YUAN Fei, and CHENG En. De-scattering and edge-enhancement algorithms for underwater image restoration[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(6): 862–871.

ANCUTI C, ANCUTI C O, HABER T, et al. Enhancing underwater images and videos by fusion[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 81–88. doi: 10.1109/cvpr.2012.6247661.

TAO Li and ASARI V K. Adaptive and integrated neighborhood-dependent approach for nonlinear enhancement of color images[J]. Journal of Electronic Imaging, 2005, 14(4): 043006. doi: 10.1117/1.2136903

PADMAVATHI G, SUBASHINI P, KUMAR M M, et al. Comparison of filters used for underwater image pre-processing[J]. International Journal of Computer Science and Network Security, 2010, 10(1): 58–65.

王彬. 基于改进等功率谱法的水下图像增强[J]. 中国科技信息, 2009(19): 46–47. doi: 10.3969/j.issn.1001-8972.2009.19.017

WANG Bin. Underwater image enhancement based on improved equal power spectral method[J]. China Science and Technology Information, 2009(19): 46–47. doi: 10.3969/j.issn.1001-8972.2009.19.017

汪荣贵, 朱静, 杨万挺, 等. 基于照度分割的局部多尺度Retinex算法[J]. 电子学报, 2010, 38(5): 1181–1186.

WANG Ronggui, ZHU Jing, YANG Wanting, et al. An improved local multi-scale Retinex algorithm based on illuminance image segmentation[J]. Acta Electronica Sinica, 2010, 38(5): 1181–1186.

李庆忠, 李长顺, 王中琦. 基于小波变换的水下降质图像复原算法[J]. 计算机工程, 2011, 37(22): 202–203, 206. doi: 10.3969/j.issn.1000-3428.2011.22.067

LI Qingzhong, LI Changshun, and WANG Zhongqi. Restoration algorithm for degraded underwater image based on wavelet transform[J]. Computer Engineering, 2011, 37(22): 202–203, 206. doi: 10.3969/j.issn.1000-3428.2011.22.067

郭相凤, 贾建芳, 杨瑞峰, 等. 基于水下图像光学成像模型的清晰化算法[J]. 计算机应用, 2012, 32(10): 2836–2839. doi: 10.3724/SP.J.1087.2012.02836

GUO Xiangfeng, JIA Jianfang, YANG Ruifeng, et al. Visibility enhancing algorithm based on optical imaging model for underwater images[J]. Journal of Computer Application, 2012, 32(10): 2836–2839. doi: 10.3724/SP.J.1087.2012.02836

ZHOU Jianjun and ZHOU Fugen. Single image dehazing motivated by Retinex theory[C]. The 2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation, Toronto, Canada, 2013: 243–247.

IQBAL K, SALAM R A, OSMAN A, et al. Underwater image enhancement using an integrated colour model[J]. International Journal of Computer Science, 2007, 34(2): 239–244.

徐岩, 马硕, 王权威. 一种利用前景模型的水下图像增强算法[J]. 小型微型计算机系统, 2017, 38(12): 2802–2806. doi: 10.3969/j.issn.1000-1220.2017.12.033

XU Yan, MA Shuo, and WANG Quanwei. Underwater image enhancement algorithm using foreground modeling[J]. Journal of Chinese Computer Systems, 2017, 38(12): 2802–2806. doi: 10.3969/j.issn.1000-1220.2017.12.033

LI Yujie, LU Huimin, LI Jianru, et al. Underwater image de-scattering and classification by deep neural network[J]. Computers & Electrical Engineering, 2016, 54: 68–77. doi: 10.1016/j.compeleceng.2016.08.008

CHIANG J Y and CHEN Yingching. Underwater image enhancement by wavelength compensation and dehazing[J]. IEEE Transactions on Image Processing, 2012, 21(4): 1756–1769. doi: 10.1109/tip.2011.2179666

汤忠强, 周波, 戴先中, 等. 基于改进DCP算法的水下机器人视觉增强[J]. 机器人, 2018, 40(2): 222–230. doi: 10.13973/j.cnki.robot.170251

TANG Zhongqiang, ZHOU Bo, DAI Xianzhong, et al. Underwater robot visual enhancements based on the improved DCP algorithm[J]. Robot, 2018, 40(2): 222–230. doi: 10.13973/j.cnki.robot.170251

FU Xueyang, ZHUANG Peixian, HUANG Yue, et al. A retinex-based enhancing approach for single underwater image[C]. IEEE International Conference on Image Processing (ICIP), Paris, France, 2014: 4572–4576. doi: 10.1109/icip.2014.7025927.

TANG Chong, VON LUKAS U F, VAHL M, et al. Efficient underwater image and video enhancement based on Retinex[J]. Signal, Image and Video Processing, 2019, 13(5): 1011–1018. doi: 10.1007/s11760-019-01439-y

杨爱萍, 张莉云, 曲畅, 等. 基于加权L₁正则化的水下图像清晰化算法[J]. 电子与信息学报, 2017, 39(3): 626–633. doi: 10.11999/JEIT160481

YANG Aiping, ZHANG Liyun, QU Chang, et al. Underwater images visibility improving algorithm with weighted L₁ regularization[J]. Journal of Electronics &Information Technology, 2017, 39(3): 626–633. doi: 10.11999/JEIT160481

LIU Peng, WANG Guoyu, QI Hao, et al. Underwater image enhancement with a deep residual framework[J]. IEEE Access, 2019, 7: 94614–94629. doi: 10.1109/access.2019.2928976

GAO Bingshao, ZHANG Ming, ZHAO Qian, et al. Underwater image enhancement using adaptive retinal mechanisms[J]. IEEE Transactions on Image Processing, 2019, 28(11): 5580–5595. doi: 10.1109/TIP.2019.2919947

杨爱萍, 郑佳, 王建, 等. 基于颜色失真去除与暗通道先验的水下图像复原[J]. 电子与信息学报, 2015, 37(11): 2541–2547. doi: 10.11999/JEIT150483

YANG Aiping, ZHENG Jia, WANG Jian, et al. Underwater image restoration based on color cast removal and dark channel prior[J]. Journal of Electronics &Information Technology, 2015, 37(11): 2541–2547. doi: 10.11999/JEIT150483

胡学龙, 张文, 胡铸鑫, 等. 一种改进的暗通道先验水下彩色图像复原算法[J]. 扬州大学学报: 自然科学版, 2018, 21(4): 37–41. doi: 10.19411/j.1007-824x.2018.04.009

HU Xuelong, ZHANG Wen, HU Zhuxin, et al. Underwater color image restoration algorithm based on improved prior dark-channel model[J]. Journal of Yangzhou University:Natural Science Edition, 2018, 21(4): 37–41. doi: 10.19411/j.1007-824x.2018.04.009

王国霖, 田建东, 李鹏越. 基于双透射率水下成像模型的图像颜色校正[J]. 光学学报, 2019, 39(9): 0901002. doi: 10.3788/AOS201939.0901002

WANG Guolin, TIAN Jiandong, and LI Pengyue. Image color correction based on double transmission underwater imaging model[J]. Acta Optica Sinica, 2019, 39(9): 0901002. doi: 10.3788/AOS201939.0901002

WEN Haocheng, TIAN Yonghong, HUANG Tiejun, et al. Single underwater image enhancement with a new optical model[C]. IEEE International Symposium on Circuits and Systems (ISCAS), Beijing, China, 2013: 753–756. doi: 10.1109/iscas.2013.6571956.

GALDRAN A, PARDO D, PICÓN A, et al. Automatic red-channel underwater image restoration[J]. Journal of Visual Communication and Image Representation, 2015, 26: 132–145. doi: 10.1016/j.jvcir.2014.11.006

蒋泽新, 朴燕. 基于电磁理论的水下图像色彩补偿[J]. 激光与光电子学进展, 2018, 55(8): 081006. doi: 10.3788/LOP55.081006

JIANG Zexin and PIAO Yan. Underwater image color compensation based on electromagnetic theory[J]. Laser &Optoelectronics Progress, 2018, 55(8): 081006. doi: 10.3788/LOP55.081006

杨爱萍, 曲畅, 王建, 等. 基于水下成像模型的图像清晰化算法[J]. 电子与信息学报, 2018, 40(2): 298–305. doi: 10.11999/JEIT170460

YANG Aiping, QU Chang, WANG Jian, et al. Underwater image visibility restoration based on underwater imaging model[J]. Journal of Electronics &Information Technology, 2018, 40(2): 298–305. doi: 10.11999/JEIT170460

WANG Keyan, HU Yan, CHEN Jun, et al. Underwater image restoration based on a parallel convolutional neural network[J]. Remote Sensing, 2019, 11(13): 1591. doi: 10.3390/rs11131591

ZHOU Linan, XIAO Yin, and CHEN Wen. Imaging through turbid media with vague concentrations based on cosine similarity and convolutional neural network[J]. IEEE Photonics Journal, 2019, 11(4): 7801315. doi: 10.1109/JPHOT.2019.2927746

LI Chongyi, GUO Jichang, and GUO Chunle. Emerging from water: underwater image color correction based on weakly supervised color transfer[J]. IEEE Signal Processing Letters, 2018, 25(3): 323–327. doi: 10.1109/LSP.2018.2792050

CHEN Xingyu, YU Junzhi, KONG Shihan, et al. Towards real-time advancement of underwater visual quality with GAN[J]. IEEE Transactions on Industrial Electronics, 2019, 66(12): 9350–9359. doi: 10.1109/TIE.2019.2893840

施引文献

资源附件(0)

访问统计