2.845

2023影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于颜色转移和自适应增益控制的混合水下图像增强

崔峥 王森 王娴 段浩 杨春曦 那靖

崔峥, 王森, 王娴, 段浩, 杨春曦, 那靖. 基于颜色转移和自适应增益控制的混合水下图像增强. 自动化学报, xxxx, xx(x): x−xx doi: 10.16383/j.aas.c240491
引用本文: 崔峥, 王森, 王娴, 段浩, 杨春曦, 那靖. 基于颜色转移和自适应增益控制的混合水下图像增强. 自动化学报, xxxx, xx(x): x−xx doi: 10.16383/j.aas.c240491
Cui Zheng, Wang Sen, Wang Xian, Duan Hao, Yang Chun-Xi, Na Jing. Hybrid underwater image enhancement based on color transfer and adaptive gain control. Acta Automatica Sinica, xxxx, xx(x): x−xx doi: 10.16383/j.aas.c240491
Citation: Cui Zheng, Wang Sen, Wang Xian, Duan Hao, Yang Chun-Xi, Na Jing. Hybrid underwater image enhancement based on color transfer and adaptive gain control. Acta Automatica Sinica, xxxx, xx(x): x−xx doi: 10.16383/j.aas.c240491

基于颜色转移和自适应增益控制的混合水下图像增强

doi: 10.16383/j.aas.c240491 cstr: 32138.14.j.aas.c240491
基金项目: 国家重点研发计划(2023YFE0204700), 国家自然科学基金(62433012, 62063011), 云南省科技厅重大专项项目(202302AD080005)资助
详细信息
    作者简介:

    崔峥:昆明理工大学机电工程学院博士研究生. 主要研究方向为水下图像增强, 计算机视觉. E-mail: cuizheng305@gmail.com

    王森:昆明理工大学机电工程学院副教授. 主要研究方向为计算机视觉, 故障诊断. E-mail: wangsen0401@126.com

    王娴:昆明理工大学机电工程学院高级实验师. 主要研究方向为自适应控制, 鲁棒控制. 本文通信作者. E-mail: wanglywxian@163.com

    段浩:昆明理工大学机电工程学院研究员. 主要研究方向为系统动力学. E-mail: duanhao705@163.com

    杨春曦:昆明理工大学机电工程学院教授. 主要研究方向为智能控制系统, 过程控制. E-mail: ycx2003@163.com

    那靖:昆明理工大学机电工程学院教授. 主要研究方向为自适应控制、参数估计、非线性控制及应用. E-mail: najing25@kust.edu.cn

Hybrid Underwater Image Enhancement Based on Color Transfer and Adaptive Gain Control

Funds: Supported by National Key R&D Program of China (2023YFE0204700), National Natural Science Foundation of China (62433012, 62063011), and Yunnan Major Scientific and Technological Projects under Grant (202302AD080005)
More Information
    Author Bio:

    CUI Zheng Ph. D. candidate at the Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology. His research interest covers underwater image enhancement and computer vision

    WANG Sen Associate Professor at the Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology. His research interest covers computer vision and fault detection

    WANG Xian Senior Lab Master at the Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology. Her research interest covers adaptive control and robust control. Corresponding author of this paper

    DUAN Hao Researcher at the Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology. His research interest covers system dynamics

    YANG Chun-Xi Professor at the Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology. His research interest covers intelligent control systems and process control

    NA Jing Professor at the Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology. His research interest covers adaptive control, parameter estimation, nonlinear control and applications

  • 摘要: 针对水下图像的颜色偏差和低对比度等退化问题, 提出了一种基于颜色转移与自适应增益控制融合的水下图像增强方法. 首先, 根据颜色转移图像和最大衰减图引导的融合策略校正水下图像的颜色偏差. 其次, 利用一阶原始对偶方法对V通道进行滤波以有效地抑制噪声的干扰, 获得结构图像; 并且提出自适应增益控制, 根据图像的高频信息自适应调整增益, 以获得细节图像. 最后, 通过加权融合结构图像与细节图像, 得到高质量的水下图像. 实验结果表明, 针对不同自然和工业环境下的水下图像, 1) 所提方法可以有效地校正颜色失真现象; 2) 显著提高水下图像的对比度并且抑制噪声干扰; 3) 在定量评价指标和高级视觉任务(目标检测、图像分割、关键点检测和水下双目测距)中优于其它主流水下图像增强方法, 为水下目标抓取等工程应用提供了有益的参考.
  • 图  1  本文提出方法的工作流程

    Fig.  1  Workflow of the proposed method

    图  2  不同颜色校正方法的定性结果

    Fig.  2  Qualitative results of different color correction methods

    图  3  不同$ \lambda $值的增强结果

    Fig.  3  Enhanced results for different $ \lambda $ values

    图  4  结构-细节图像示例

    Fig.  4  Example of structure-detail image

    图  5  不同最大增益值的增强结果

    Fig.  5  Enhanced results using different maximum gain values

    图  6  基于颜色转移的水下颜色校正方法的增强图像

    Fig.  6  Enhanced results of the underwater color correction method based on color transfer

    图  7  不同主流方法在UIEB数据集上的视觉对比

    Fig.  7  Visual comparisons of different mainstream methods on the UIEB dataset

    图  9  不同主流方法在RISU数据集上的视觉对比

    Fig.  9  Visual comparisons of different mainstream methods on the RISU dataset

    图  10  不同方法在UIEB数据集上的细节对比

    Fig.  10  Detailed comparison of different methods on the UIEB dataset

    图  11  水下图像目标检测的应用示例

    Fig.  11  Application examples of underwater image object detection

    图  12  水下图像分割的应用示例

    Fig.  12  Application examples of underwater image segmentation

    图  13  关键点检测的应用示例

    Fig.  13  Application examples of keypoint detection

    图  14  各组件在不同退化水下图像上的视觉消融结果

    Fig.  14  Visual ablation results of each component on different degraded underwater images

    图  15  原始水下棋盘格图像的部分示例

    Fig.  15  Partial examples of raw underwater checkerboard images

    图  16  不同主流方法在双目棋盘格图像上的视觉对比

    Fig.  16  Visual comparison of different mainstream methods on binocular checkerboard images

    图  8  整体实验设备

    Fig.  8  Overall experimental equipment

    表  1  基于UIQM指标的定量结果

    Table  1  Quantitative results based on UIQM metrics

    IBLAGDCPUNTVSea-thruMLLEBRUIEWaterNet本文方法
    image13.7393.4253.8684.3404.7515.1834.3074.971
    image24.6935.1743.7194.6654.1494.7423.6314.848
    image32.4511.2233.6962.8763.5453.9953.0573.834
    image41.9912.9062.9922.5512.7764.0022.7872.862
    image52.5101.7625.7684.3954.8415.1134.5805.313
    image63.3001.7274.8834.4604.7015.2593.9715.110
    image74.0521.7814.8624.3334.7565.2484.0784.902
    image83.5142.7715.1185.0194.7455.2424.4935.396
    下载: 导出CSV

    表  2  定量比较不同算法在目标检测上的性能

    Table  2  Quantitative comparison of the performance of different mainstream methods on object detection

    AP$(\%)$ $AP_{50}$$(\%)$ $AP_{75}$$(\%)$ $AR_{1}$$(\%)$ $AR_{10}$$(\%)$ $AR_{100}$$(\%)$
    IBLA 0.502 0.856 0.524 0.168 0.554 0.618
    GDCP 0.493 0.854 0.516 0.159 0.531 0.588
    UNTV 0.509 0.873 0.513 0.168 0.552 0.606
    Sea-thru 0.499 0.862 0.506 0.164 0.548 0.601
    MLLE 0.509 0.871 0.530 0.161 0.550 0.599
    BRUIE 0.499 0.859 0.529 0.154 0.538 0.597
    WaterNet 0.501 0.862 0.515 0.162 0.532 0.591
    本文方法 0.514 0.871 0.558 0.167 0.551 0.609
    下载: 导出CSV

    表  3  各组件的定量消融结果

    Table  3  Quantitative ablation results of each component

    image1image2image3image4image5
    无颜色校正方法4.5390.4754.8041.5733.584
    无最大衰减图5.1603.8025.0134.4654.474
    无细节增强方法4.3562.4654.2443.2774.152
    无细节图像4.9913.4024.5174.1884.434
    完整方法5.2464.1315.0294.9214.517
    下载: 导出CSV

    表  4  水下视觉测量

    Table  4  Measurement of underwater vision

    RawIBLAGDCPUNTVSea-thruMLLEBRUIEWaterNet本文方法
    RE (像素)0.1660.1830.1740.3200.2240.1620.1850.1780.133
    AD (mm)28.3828.5728.6026.5928.6528.3828.6228.5628.87
    下载: 导出CSV
  • [1] Raveendran S, Patil M D, Birajdar G K. Underwater image enhancement: a comprehensive review, recent trends, challenges and applications. Artificial Intelligence Review, 2021, 54: 5413−5467 doi: 10.1007/s10462-021-10025-z
    [2] 刘妹琴, 韩学艳, 张森林, 郑荣濠, 兰剑. 基于水下传感器网络的目标跟踪技术研究现状与展望. 自动化学报, 2021, 47(2): 235−251

    Liu Mei-Qin, Han Xue-Yan, Zhang Sen-Lin, Zheng Rong-Hao, Lan Jian. Research status and prospect of target tracking technologies via underwater sensor networks. Acta Automatica Sinica, 2021, 47(2): 235−251
    [3] Yang M, Hu J T, Li C Y, Gustavo R, Du Y X, Hu K. An in-depth survey of underwater image enhancement and restoration. IEEE Access, 2019, 7: 123638−123657 doi: 10.1109/ACCESS.2019.2932611
    [4] 徐璠, 王贺升. 软体机械臂水下自适应鲁棒视觉伺服. 自动化学报, 2023, 49(4): 744−753

    Xu Fan, Wang He-Sheng. Adaptive robust visual servoing control of a soft manipulator in underwater environment. Acta Automatica Sinica, 2023, 49(4): 744−753
    [5] He K M, Sun J, Tang X O. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341−2353
    [6] Drews P, Nascimento E, Moraes F, Botelho S, Campos M. Transmission estimation in underwater single images. In: Proceedings of the international conference on computer vision workshops. IEEE, 2013. 825−830
    [7] Galdran A, Pardo D, Picón A, Alvarez A. Automatic Red-Channel underwater image restoration. Journal of Visual Communication and Image Representation, 2015, 26: 132−145 doi: 10.1016/j.jvcir.2014.11.006
    [8] 谢昊伶, 彭国华, 王凡, 杨成. 基于背景光估计与暗通道先验的水下图像复原. 光学学报, 2018, 38(1): 18−27

    Xie H L, Peng G H, Wang F, Yang C. Underwater image restoration based on background light estimation and dark channel prior. Acta Optica Sinica, 2018, 38(1): 18−27
    [9] Carlevaris-Bianco N, Mohan A, Eustice R M. Initial results in underwater single image dehazing. In: Proceedings of the 2010 OCEANS. Seattle, WA, USA: IEEE, 2010. 1−8
    [10] Peng Y T, Cosman P C. Underwater image restoration based on image blurriness and light absorption. IEEE transactions on image processing, 2017, 26(4): 1579−1594 doi: 10.1109/TIP.2017.2663846
    [11] Berman D, Levy D, Avidan S, Treibitz T. Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset. IEEE transactions on pattern analysis and machine intelligence, 2020, 43(8): 2822−2837
    [12] Xie J, Hou G J, Wang G D, Pan Z K. A variational framework for underwater image dehazing and deblurring. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 32(6): 3514−3526
    [13] Ancuti C O, Ancuti C, De Vleeschouwer C, Bekaert P. Color balance and fusion for underwater image enhancement. IEEE Transactions on Image Processing, 2018, 27(1): 379−393 doi: 10.1109/TIP.2017.2759252
    [14] Zhang W, Zhuang P, Sun H H, Li G H, Kwong S, Li C Y. Underwater Image Enhancement via Minimal Color Loss and Locally Adaptive Contrast Enhancement. IEEE Transactions on Image Processing, 2022, 31: 3997−4010
    [15] Zhuang P X, Li C Y, Wu J M. Bayesian retinex underwater image enhancement. Engineering Applications of Artificial Intelligence, 2021, 101: 104171 doi: 10.1016/j.engappai.2021.104171
    [16] Ghani A S A, Isa N A M. Underwater image quality enhancement through Rayleigh-stretching and averaging image planes. International Journal of Naval Architecture and Ocean Engineering, 2014, 6(4): 840−866 doi: 10.2478/IJNAOE-2013-0217
    [17] 杨淼, 纪志成. 基于模糊形态筛和四元数的水下彩色图像增强. 仪器仪表学报, 2012, 33(7): 1601−1605

    Yang M, Ji Z C. Underwater color image enhancement based on quaternion and fuzzy morphological sieves. Journal of Scientific Instrument, 2012, 33(7): 1601−1605
    [18] 李庆忠, 白文秀, 牛炯. 基于改进CycleGAN的水下图像颜色校正与增强. 自动化学报, 2023, 49(4): 820−829

    Li Qing-Zhong, Bai Wen-Xiu, Niu Jiong. Underwater image color correction and enhancement based on improved cycle-consistent generative adversarial networks. Acta Automatica Sinica, 2023, 49(4): 820−829
    [19] Li C Y, Guo C L, Ren W Q, Cong R M, Hou J H, Kwang S, et al. An Underwater Image Enhancement Benchmark Dataset and Beyond. IEEE Transactions on Image Processing, 2019, 29: 4376−4389
    [20] Islam M J, Xia Y, Sattar J. Fast underwater image enhancement for improved visual perception. IEEE Robotics and Automation Letters, 2020, 5(2): 3227−3234 doi: 10.1109/LRA.2020.2974710
    [21] McGlamery B L. A computer model for underwater camera systems. In: Proceedings of SPIE, 1980, 208 : 221−231
    [22] Jaffe J S. Computer modeling and the design of optimal underwater imaging systems. IEEE Journal of Oceanic Engineering, 1990, 15(2): 101−111
    [23] Reinhard E, Adhikhmin M, Gooch B, Shirley P. Color transfer between images. IEEE Computer graphics and applications, 2001, 21(5): 34−41
    [24] Chambolle A, Pock T. A first-order primal-dual algorithm for convex problems with applications to imaging. Journal of mathematical imaging and vision, 2011, 40: 120−145 doi: 10.1007/s10851-010-0251-1
    [25] Tarik A, Salih D, Yucel A. A Histogram Modification Framework and Its Application for Image Contrast Enhancement. IEEE Transactions on Image Processing, 2009, 18(9): 1921−1935 doi: 10.1109/TIP.2009.2021548
    [26] Deng G. A generalized unsharp masking algorithm. IEEE transactions on Image Processing, 2010, 20(5): 1249−1261
    [27] Peng Y T, Cao K, Cosman P C. Generalization of the dark channel prior for single image restoration. IEEE Transactions on Image Processing, 2018, 27(6): 2856−2868
    [28] Akkaynak D, Treibitz T. Sea-thru: A method for removing water from underwater images. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019. 1682−1691
    [29] Ranftl R, Lasinger K, Hafner D, Schindler K, Koltun V. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 44(3): 1623−1637
    [30] Panetta K, Gao C, Agaian S. Human-visual-system-inspired underwater image quality measures. IEEE Journal of Oceanic Engineering, 2015, 41(3): 541−551
    [31] Li C Y, Li L L, Jiang H L, Weng K H, Geng Y F, Li L, et al. YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. ArXiv Preprint ArXiv: 2209.02976. 2022
    [32] Jiang L H, Wang Y, Jia Q, Xu S W, Liu Y, Fan X, et al. Underwater Species Detection using Channel Sharpening Attention. In: Proceedings of the 29th ACM International Conference on Multimedia. 2021. 4259−4267
    [33] Lei T, Jia X H, Zhang Y N, Liu S G, Meng H Y, Nandi A K. Superpixel-Based Fast Fuzzy C-Means Clustering for Color Image Segmentation. IEEE Transactions on Fuzzy Systems, 2019, 27(9): 1753−1766 doi: 10.1109/TFUZZ.2018.2889018
    [34] Bay H, Tuytelaars T, Van Gool L. Surf: Speeded up robust features. In: Proceedings of the european conference on computer vision. 2006. 404−417
    [35] Pedersen M, Bengtson S H, Gade R, Madsen N, Mieslund T B. Camera Calibration for Underwater 3D Reconstruction Based on Ray Tracing Using Snell's Law. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 2018. 1410−1417
  • 加载中
计量
  • 文章访问数:  68
  • HTML全文浏览量:  43
  • 被引次数: 0
出版历程
  • 收稿日期:  2024-07-15
  • 录用日期:  2024-11-16
  • 网络出版日期:  2024-11-22

目录

    /

    返回文章
    返回