Restoration of Underwater Distorted Image Sequence Based on Generative Adversarial Network

被引:0
|
作者
He, Changxin [1 ]
Zhang, Zhen [1 ]
机构
[1] Shanghai Univ, Sch Mechatron Engn & Automat, Shanghai, Peoples R China
来源
PROCEEDINGS OF 2019 IEEE 8TH JOINT INTERNATIONAL INFORMATION TECHNOLOGY AND ARTIFICIAL INTELLIGENCE CONFERENCE (ITAIC 2019) | 2019年
关键词
image restoration; distorted image; turbulence; generative adversarial network;
D O I
10.1109/itaic.2019.8785496
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Underwater images will be distorted due to the influence of turbulence, and images will appear geometric distortion since the light is refracted by the turbulence, which makes task of image recognition difficult. In order to improve image recognition underwater, this paper proposes an image restoration method using underwater distorted image sequence through deep learning technique. Considering the complexity of dynamics motion, image sequence is more feasible to realize task of restoration, which contains enough information of water turbulence. Generative adversarial network as a deep neural network has proved to be an appropriate method applying to the field of image processing, which is used to restore the distorted image. Experiment shows the proposed method has fine ability of using distorted image sequence to realize image restoration.
引用
收藏
页码:866 / 870
页数:5
相关论文
共 50 条
  • [1] Underwater image restoration based on perceptually optimized generative adversarial network
    Wang, Peng
    Chen, Haixiu
    Xu, Weihua
    Jin, Suqin
    JOURNAL OF ELECTRONIC IMAGING, 2020, 29 (03)
  • [2] Vehicle radiation image restoration based on a generative adversarial network
    Leng Z.
    Sun Y.
    Tong J.
    Wang Z.
    Qinghua Daxue Xuebao/Journal of Tsinghua University, 2022, 62 (10): : 1691 - 1696
  • [3] Underwater-GAN: Underwater Image Restoration via Conditional Generative Adversarial Network
    Yu, Xiaoli
    Qu, Yanyun
    Hong, Ming
    PATTERN RECOGNITION AND INFORMATION FORENSICS, 2019, 11188 : 66 - 75
  • [4] Constrained adversarial loss for generative adversarial network-based faithful image restoration
    Kim, Dong-Wook
    Chung, Jae-Ryun
    Kim, Jongho
    Lee, Dae Yeol
    Jeong, Se Yoon
    Jung, Seung-Won
    ETRI JOURNAL, 2019, 41 (04) : 415 - 425
  • [5] Restoration of Distorted Laser-Spot Image based on Generative Adversarial Networks
    Diao, Shuiqiu
    Li, Jianjun
    Zhang, Rui
    Wen, Feng
    Wu, Baojian
    Qiu, Kun
    2024 13TH INTERNATIONAL CONFERENCE ON COMMUNICATIONS, CIRCUITS AND SYSTEMS, ICCCAS 2024, 2024, : 543 - 547
  • [6] Underwater Image Enhancement Based on Multiscale Generative Adversarial Network
    Lin Sen
    Liu Shiben
    LASER & OPTOELECTRONICS PROGRESS, 2021, 58 (16)
  • [7] Underwater image enhancement method based on the generative adversarial network
    Yu, Jin-Tao
    Jia, Rui-Sheng
    Gao, Li
    Yin, Ruo-Nan
    Sun, Hong-Mei
    Zheng, Yong-Guo
    JOURNAL OF ELECTRONIC IMAGING, 2021, 30 (01)
  • [8] Underwater Image Enhancement Based on Generative Adversarial Network with Preprocessed Image Penalty
    Song Wei
    Xing Jingjing
    Du Yanling
    He Qi
    LASER & OPTOELECTRONICS PROGRESS, 2021, 58 (12)
  • [9] Image and Graph Restoration Dependent on Generative Adversarial Network Algorithm
    Cao, Yuanhao
    TEHNICKI VJESNIK-TECHNICAL GAZETTE, 2021, 28 (06): : 1820 - 1824
  • [10] Underwater image enhancement based on multiscale fusion generative adversarial network
    Dai, Yating
    Wang, Jianyu
    Wang, Hao
    He, Xin
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024, 15 (04) : 1331 - 1341