基于Inception-Residual和生成对抗网络的水下图像增强

王德兴; 王越; 袁红春

doi:10.37188/CJLCD.2021-0058

您当前的位置：

首页 >

文章列表页 >

基于Inception-Residual和生成对抗网络的水下图像增强

图像增强与分割 | 更新时间：2021-11-08

- 基于Inception-Residual和生成对抗网络的水下图像增强
- Underwater image enhancement based on Inception-Residual and generative adversarial network
- 液晶与显示 2021年36卷第11期页码：1474-1485
- 作者机构：
  
  上海海洋大学信息学院, 上海 201306
- 作者简介：
  
  [ "王德兴(1968-)，男，河北保定人，博士，副教授，2007年于合肥工业大学获得博士学位，主要从事人工智能、模式识别和数据挖掘方面的研究。E-mail: dxwang@shou.edu.cn" ]
  [ "袁红春(1971-)，男，江苏海门人，博士，教授，2002年于中国科学技术大学获得博士学位，主要从事智能信息处理和人工智能方面的研究。E-mail: hcyuan@shou.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(41776142)
- DOI：10.37188/CJLCD.2021-0058
  中图分类号： TP391.41
- 收稿日期：2021-03-01，
  
  修回日期：2021-03-29，
  
  纸质出版日期：2021-11
- 稿件说明：
移动端阅览
王德兴, 王越, 袁红春. 基于Inception-Residual和生成对抗网络的水下图像增强[J]. 液晶与显示, 2021,36(11):1474-1485.

De-xing WANG, Yue WANG, Hong-chun YUAN. Underwater image enhancement based on Inception-Residual and generative adversarial network[J]. Chinese journal of liquid crystals and displays, 2021, 36(11): 1474-1485.
王德兴, 王越, 袁红春. 基于Inception-Residual和生成对抗网络的水下图像增强[J]. 液晶与显示, 2021,36(11):1474-1485. DOI： 10.37188/CJLCD.2021-0058.

De-xing WANG, Yue WANG, Hong-chun YUAN. Underwater image enhancement based on Inception-Residual and generative adversarial network[J]. Chinese journal of liquid crystals and displays, 2021, 36(11): 1474-1485. DOI： 10.37188/CJLCD.2021-0058.

摘要

为解决光在水下传播过程中由吸收与散射效应导致的水下图像模糊、对比度低和颜色失真问题，提出一种基于Inception-Residual和生成对抗网络的水下图像增强算法。首先，将退化水下图像缩放至256×256×3大小，以获得用于训练模型的数据集。接着，将Inception模块、残差思想、编码解码结构和生成对抗网络相结合，构建IRGAN (Generative Adversarial Network with Inception-Residual)模型来增强水下图像。然后，利用全局相似性、内容感知和色彩感知构造多项损失函数，约束生成网络和判别网络的对抗训练。最后，通过训练好的模型对退化水下图像进行处理以获得清晰的水下图像。实验结果表明：与现有增强方法相比，所提算法增强的水下图像在PSNR、UIQM和IE指标上的平均值分别比第二名提升13.6%、4.1%和0.9%。在主观感知和客观评估中，增强后的水下图像在清晰度、对比度增强和颜色校正方面均得到改善。

Abstract

To solve the blurring

low contrast and color distortion problem of underwater image caused by light absorption and scattering effects in the underwater environment

an underwater image enhancement algorithm based on the Inception-Residual and generative adversarial network is proposed. Firstly

the degraded underwater image is scaled to a size of 256×256×3 to obtain a data set for the training model. The Inception module

residual idea

encoding and decoding structure and generative adversarial network are combined to build an IRGAN(Generative Adversarial Network with Inception-Residual) model to enhance underwater images. Then

a multi-loss function including global similarity

content perception and color perception is constructed to constrain the antagonistic training of generative network and discriminant network. Finally

the degraded underwater image is processed by the trained model to obtain a clear underwater image. The experimental results show that

compared with the existing enhancement methods

the average values of the PSNR

UIQM and IE indicators of the underwater images enhanced by the proposed algorithm are improved by 13.6%

4.1% and 0.9%

respectively

compared with the second place. In subjective perception and objective evaluation

the sharpness

contrast enhancement and color correction of the enhanced underwater image are improved.

关键词

Keywords

references

X M WANG , Q M LI , J W YIN , 等 . An adaptive denoising and detection approach for underwater sonar image . Remote Sensing , 2019 . 11 ( 4 ): 396 DOI: 10.3390/rs11040396 http://doi.org/10.3390/rs11040396 .

ZENG L C, SUN B, ZHANG W, et al . Underwater image target detection with cascade classifier and image preprocessing method[C]//12 th International Conference on Intelligent Robotics and Applications . Shenyang: Springer, 2019: 195-205.

徐岩 , 孙美双 . 基于卷积神经网络的水下图像增强方法 . 吉林大学学报(工学版) , 2018 . 48 ( 6 ): 1895 - 1903 . https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201806034.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201806034.htm .

Y XU , M S SUN . Enhancing underwater image based on convolutional neural networks . Journal of Jilin University (Engineering and Technology Edition) , 2018 . 48 ( 6 ): 1895 - 1903 . https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201806034.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201806034.htm .

W D XIANG , P YANG , S WANG , 等 . Underwater image enhancement based on red channel weighted compensation and gamma correction model . Opto-Electronic Advances , 2018 . 1 ( 10 ): 180024 http://www.oejournal.org/J/PDFFullDown/A190111000003?lang=cn http://www.oejournal.org/J/PDFFullDown/A190111000003?lang=cn .

D BERMAN , D LEVY , S AVIDAN , 等 . Underwater single image color restoration using haze-lines and a new quantitative dataset . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2021 . 43 ( 8 ): 2822 - 2837 . http://www.researchgate.net/publication/339632700_Underwater_Single_Image_Color_Restoration_Using_Haze-Lines_and_a_New_Quantitative_Dataset http://www.researchgate.net/publication/339632700_Underwater_Single_Image_Color_Restoration_Using_Haze-Lines_and_a_New_Quantitative_Dataset .

X Y DENG , H G WANG , X LIU . Underwater image enhancement based on removing light source color and dehazing . IEEE Access , 2019 . 7 114297 - 114309 . DOI: 10.1109/ACCESS.2019.2936029 http://doi.org/10.1109/ACCESS.2019.2936029 .

PROTASIUK R, BIBI A, GHANEM B. Local color mapping combined with color transfer for underwater image enhancement[C]//2019 IEEE Winter Conference on Applications of Computer Vision ( WACV ). Waikoloa: IEEE, 2019: 1433-1439.

王一斌 , 尹诗白 , 吕卓纹 . 自适应背景光估计与非局部先验的水下图像复原 . 光学精密工程 , 2019 . 27 ( 2 ): 499 - 510 . https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201902026.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201902026.htm .

Y B WANG , S B YIN , Z W LYU . Underwater image restoration with adaptive background light estimation and non-local prior . Optics and Precision Engineering , 2019 . 27 ( 2 ): 499 - 510 . https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201902026.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201902026.htm .

范之国 , 宋强 , 代晴晴 , 等 . 全局参数估计的水下目标偏振复原方法 . 光学精密工程 , 2018 . 26 ( 7 ): 1621 - 1632 . https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201807008.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201807008.htm .

Z G FAN , Q SONG , Q Q DAI , 等 . Underwater target polarization recovery method based on global parameter estimation . Optics and Precision Engineering , 2018 . 26 ( 7 ): 1621 - 1632 . https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201807008.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201807008.htm .

GVRAKSIN G E, KÖSE U, DEPERLIOLU Ö. Underwater image enhancement based on contrast adjustment viadifferential evolution algorithm[C]//2016 International Symposium on Innovations in Intelligent Systems and Applications . Sinaia: IEEE, 2016: 1-5.

S VASAMSETTI , N MITTAL , B C NEELAPU , 等 . Wavelet based perspective on variational enhancement technique for underwater imagery . Ocean Engineering , 2017 . 141 88 - 100 . DOI: 10.1016/j.oceaneng.2017.06.012 http://doi.org/10.1016/j.oceaneng.2017.06.012 .

代成刚 , 林明星 , 王震 , 等 . 基于亮通道色彩补偿与融合的水下图像增强 . 光学学报 , 2018 . 38 ( 11 ): 1110003 https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201811011.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201811011.htm .

C G DAI , M X LIN , Z WANG , 等 . Color compensation based on bright channel and fusion for underwater image enhancement . Acta Optica Sinica , 2018 . 38 ( 11 ): 1110003 https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201811011.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201811011.htm .

邹沛煜 , 张卫东 , 史金余 , 等 . 基于高低频分量融合的水下图像增强算法 . 激光与光电子学进展 , 2020 . 57 ( 16 ): 161010 https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202016014.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202016014.htm .

P Y ZOU , W D ZHANG , J Y SHI , 等 . Underwater image enhancement algorithm based on fusion of high and low frequency components . Laser & Optoelectronics Progress , 2020 . 57 ( 16 ): 161010 https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202016014.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202016014.htm .

C Y LI , S ANWAR , F PORIKLI . Underwater scene prior inspired deep underwater image and video enhancement . Pattern Recognition , 2020 . 98 107038 DOI: 10.1016/j.patcog.2019.107038 http://doi.org/10.1016/j.patcog.2019.107038 .

C Y LI , C L GUO , W Q REN , 等 . An underwater image enhancement benchmark dataset and beyond . IEEE Transactions on Image Processing , 2020 . 29 4376 - 4389 . DOI: 10.1109/TIP.2019.2955241 http://doi.org/10.1109/TIP.2019.2955241 .

FABBRI C, ISLAM M J, SATTAR J. Enhancing underwater imagery using generative adversarial networks[C]//2018 IEEE International Conference on Robotics and Automation ( ICRA ). Brisbane: IEEE, 2018: 7159-7165.

YU X L, QU Y Y, HONG M. Underwater-GAN: underwater image restoration via conditional generative adversarial network[C]// ICPR 2018 International Conference on Pattern Recognition . Beijing: Springer, 2018: 66-75.

HE K M, ZHANG X Y, REN S Q, et al . Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas: IEEE, 2016: 770-778.

P LIU , G Y WANG , H QI , 等 . Underwater image enhancement with a deep residual framework . IEEE Access , 2019 . 7 94614 - 94629 . DOI: 10.1109/ACCESS.2019.2928976 http://doi.org/10.1109/ACCESS.2019.2928976 .

M J ISLAM , Y Y XIA , J SATTAR . Fast underwater image enhancement for improved visual perception . IEEE Robotics and Automation Letters , 2020 . 5 ( 2 ): 3227 - 3234 . DOI: 10.1109/LRA.2020.2974710 http://doi.org/10.1109/LRA.2020.2974710 .

DUDHANE A, AULAKH H S, MURALA S. RI-GAN: an end-to-end network for single image haze removal[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops ( CVPRW ). Long Beach: IEEE, 2019: 2014-2023.

LI C, WAND M. Precomputed real-time texture synthesis with Markovian generative adversarial networks[C]//14 th European Conference on Computer Vision . Amsterdam: Springer, 2016: 702-716.

ISOLA P, ZHU J Y, ZHOU T H, et al . Image-to-image translation with conditional adversarial networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Honolulu: IEEE, 2017: 5967-5976.

JOHNSON J, ALAHI A, LI F F. Perceptual losses for real-time style transfer and super-resolution[C]//14 th European Conference on Computer Vision . Amsterdam: Springer, 2016: 694-711.

IGNATOV A, KOBYSHEV N, TIMOFTE R, et al . DSLR-quality photos on mobile devices with deep convolutional networks[C]//2017 IEEE International Conference on Computer Vision (ICCV) . Venice: IEEE, 2017: 3297-3305.

CHEN Y S, WANG Y C, KAO M H, et al . Deep Photo Enhancer: unpaired learning for image enhancement from photographs with GANs[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City: IEEE, 2018: 6306-6314.

HORÉ A, ZIOU D. Image quality metrics: PSNR vs. SSIM[C]//2010 20 th International Conference on Pattern Recognition . Istanbul: IEEE, 2010: 2366-2369.

K PANETTA , C GAO , S AGAIAN . Human-visual-system-inspired underwater image quality measures . IEEE Journal of Oceanic Engineering , 2016 . 41 ( 3 ): 541 - 551 . DOI: 10.1109/JOE.2015.2469915 http://doi.org/10.1109/JOE.2015.2469915 .

L X LIU , Y HUA , Q J ZHAO , 等 . Blind image quality assessment by relative gradient statistics and adaboosting neural network . Signal Processing: Image Communication , 2016 . 40 1 - 15 . DOI: 10.1016/j.image.2015.10.005 http://doi.org/10.1016/j.image.2015.10.005 .

A MITTAL , R SOUNDARARAJAN , A C BOVIK . Making a "completely blind" image quality analyzer . IEEE Signal Processing Letters , 2013 . 20 ( 3 ): 209 - 212 . DOI: 10.1109/LSP.2012.2227726 http://doi.org/10.1109/LSP.2012.2227726 .

浏览量

173

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

结合特征融合与物理校正的水下图像增强方法

基于卷积稀疏编码与生成对抗网络的图像超分辨率重建