基于领域自适应的水下图像增强算法

doi:10.3969/j.issn.1006-2475.2024.10.009

摘要/Abstract

摘要： 水下图像增强是完成水下任务的关键技术。针对水下图像存在的颜色失真、图像模糊的问题，本文设计一种基于领域自适应的水下图像增强算法（Underwater Domain Adaptation Network， UDA Net），实现无监督条件下水下图像的有效增强，显著改善原始水下图像的清晰度。该算法基于U-Net网络框架，利用卷积神经网络和多头注意力机制进行特征提取，引入对抗学习思想，在领域特征提取模块与输出模块中加入判别网络，同时优化源域特征增强损失、特征对齐损失以及输出对齐损失，保证源域到目标域的风格迁移与特征对齐，实现水下增强效果。此外，利用公开的水下数据集EUVP、UIEB以及UFO-120进行实验验证，并与前沿的增强算法进行对比实验，实验结果均表明了本文UDA Net算法的有效性，并在水下图像增强任务上具有良好的应用前景。

关键词: 水下图像增强, 风格迁移, 对抗学习, 损失函数

Abstract: Underwater image enhancement is a key technology for underwater missions. Aiming at the problems of color distortion and image blurring in underwater images， this paper designs an underwater domain adaptation network (UDA Net) based on the domain adaptive method to achieve effective enhancement of underwater images under unsupervised conditions. The sharpness of the original underwater images is significantly improved. Based on U-Net network framework， the algorithm uses convolutional neural network and multi-head attention mechanism for feature extraction， introduces adversarial learning idea， and adds discrimination network to domain feature extraction module and output module. Meanwhile， it optimizes feature enhancement loss， feature alignment loss and output alignment loss in the source domain to ensure style transfer and feature alignment from the source domain to the target domain， achieving underwater enhancement. In addition， the public underwater data sets EUVP， UIEB and UFO-120 are used for experimental verification， and the experimental results are compared with cutting-edge enhancement algorithms. The effectiveness of UDA Net algorithm is proved， and it has a good application prospect in underwater image enhancement tasks.

Key words: , , underwater image enhancement； style transfer； adversarial learning； loss function

中图分类号:

TN929.3

杜菲瑀, 王海燕, 姚海洋, 陈晓. 基于领域自适应的水下图像增强算法[J]. 计算机与现代化, 2024, 0(10): 55-60.

DU Feiyu, WANG Haiyan, YAO Haiyang, CHEN Xiao. Domain Adaption-based Underwater Image Enhancement Algorithm[J]. Computer and Modernization, 2024, 0(10): 55-60.

参考文献

［1］ FU X Y， FAN Z W， LING M， et al. Two-step approach for single underwater image enhancement［C］// 2017 International Symposium on Intelligent Signal Processing and Communication Systems（ISPACS）. IEEE， 2017：789-794.
［2］ FABBRI C， ISLAM M J， Sattar J. Enhancing underwater imagery using generative adversarial networks［C］// 2018 IEEE International Conference on Robotics and Automation （ICRA）. IEEE， 2018：7159-7165.
［3］ LI C Y， GUO C L， REN W Q， et al. An underwater image enhancement benchmark dataset and beyond［J］. IEEE Transactions on Image Processing， 2019，29：4376-4389.
［4］ LI C Y， ANWAR S， PORIKLI F. Underwater scene prior inspired deep underwater image and video enhancement［J］. Pattern Recognition， 2020，98. DOI: 10.1016/j.patcog.
2019.107038.
［5］ SONG W， WANG Y， HUANG D M， et al. Enhancement of underwater images with statistical model of background light and optimization of transmission map［J］. IEEE Transactions on Broadcasting， 2020，66（1）：153-169.
［6］ LI C Y， ANWAR S， HOU J H， et al. Underwater image enhancement via medium transmission-guided multi-color space embedding［J］. IEEE Transactions on Image Processing， 2021，30：4985-5000.
［7］ JIANG N F， CHEN W L， LIN Y T， et al. Underwater image enhancement with lightweight cascaded network［J］. IEEE Transactions on Multimedia， 2021，24：4301-4313.
［8］ XIE J， HOU G J， WANG G D， et al. A variational framework for underwater image dehazing and deblurring［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2022，32（6）：3514-3526.
［9］ JIANG Q， ZHANG Y F， BAO F X， et al. Two-step domain adaptation for underwater image enhancement［J］. Pattern Recognition， 2022，122. DOI: 10.1016/j.patcog.2021.108324.
［10］ WANG Z Y， SHEN L Q， XU M， et al. Domain adaptation for underwater image enhancement［J］. IEEE Transactions on Image Processing， 2023，32：1442-1457.
［11］ ZHOU J C， LI B S， ZHANG D H， et al. UGIF-Net： An efficient fully guided information flow network for underwater image enhancement［J］. IEEE Transactions on Geoscience and Remote Sensing， 2023，61. DOI: 10.1109/TGRS.2023.
3293912.
［12］ VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. ACM， 2017：6000-6010.
［13］ RONNEBERGER O， FISCHER P， BROX T. U-Net： Convolutional networks for biomedical image segmentation［C］// Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015：18th International Conference. Springer， 2015：234-241.
［14］ PANG T Y， YANG X， DONG Y P， et al. Boosting adversarial training with hypersphere embedding［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. ACM， 2020：7779-7792.
［15］ GAN Z， CHEN Y C， LI L J， et al. Large-scale adversarial training for vision-and-language representation learning［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. ACM， 2020：6616
-6628.
［16］ WANG H T， CHEN T L， GUI S P， et al. Once-for-all adversarial training： In-situ tradeoff between robustness and accuracy for free［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems.ACM， 2020：7449-7461.
［17］ WEN L F， GAO C Y， ZOU C Q. CAP-VSTNet： Content affinity preserved versatile style transfer［C］// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2023：18300-18309.
［18］ KE Z H， LIU Y H， ZHU L， et al. Neural preset for color style transfer［C］// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2023：14173-14182.
［19］ ZAMIR S W， ARORA A， KHAN S， et al. Restormer： Efficient transformer for high-resolution image restoration［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2022：5728-5739.
［20］ WU Q F， CHEN Y P， MENG J. DCGAN-based data augmentation for tomato leaf disease identification［J］. IEEE Access， 2020，8：98716-98728.
［21］ WANG Y X， WU C S， HERRANZ L， et al. Transferring GANs： Generating images from limited data［C］// Proceedings of the 15th European Conference on Computer Vision （ECCV）. Springer， 2018：220-236.
［22］ KINGMA D P， BA J. Adam： A method for stochastic optimization［J］. arXiv preprint arXiv：1412.6980， 2014.
［23］ LI B Y， WU F， LIM S N， et al. On feature normalization and data augmentation［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2021：12378-12387.
［24］ ZHAO H， GALLO O， FROSIO I， et al. Loss functions for neural networks for image processing［J］. IEEE Transactions on Computational Imaging， 2017，3（1）：47-57.
［25］ YANG M， SOWMYA A. An underwater color image quality evaluation metric［J］. IEEE Transactions on Image Processing， 2015，24（12）：6062-6071.
［26］ ISLAM M J， XIA Y Y， SATTAR J. Fast underwater image enhancement for improved visual perception［J］. IEEE Robotics and Automation Letters， 2020，5（2）：3227-3234.
［27］ ISLAM M J， LUO P G， SATTAR J. Simultaneous enhancement and super-resolution of underwater imagery for improved visual perception［J］. Proceedings of Robotics： Science and Systems， 2020，16：188-198.

[1]	陈凯1, 李宜汀1, 2, 全华凤1 . 基于改进YOLOv8的河道废弃瓶检测方法[J]. 计算机与现代化, 2024, 0(11): 113-120.
[2]	钟海龙1, 2, 何月顺1, 何璘琳1, 陈杰1, 田鸣3, 郑瑞银4. 基于代价敏感卷积神经网络的加密流量分类#br# #br#[J]. 计算机与现代化, 2024, 0(05): 55-60.
[3]	刘馨嫔1, 2, 3, 王洪1, 3, 赵良瑾1, 3. 基于多任务学习的近岸舰船检测方法[J]. 计算机与现代化, 2024, 0(03): 29-33.
[4]	. 基于反向残差注意力的光流估计[J]. 计算机与现代化, 2024, 0(02): 64-68.
[5]	李国鑫, 曲寒冰, 朱成博, 王鑫轩, 胡嘉宝. 基于联合网络的域适应行人重识别算法[J]. 计算机与现代化, 2023, 0(06): 48-55.
[6]	陈明瑶, 徐琨, 李晓旋. 基于风格迁移的手势分割方法[J]. 计算机与现代化, 2021, 0(05): 20-25.
[7]	李雨妮，王鹏，肖建力. 一种使用多维度直方图匹配的图像风格迁移算法[J]. 计算机与现代化, 2019, 0(02): 15-.