基于多背景光融合和红通道先验理论的水下图像复原

胡 登洋, 李 晨滔, 刘 思玮
广西师范大学

摘要


针对水下图像普遍模糊,细节不突出,颜色失真等问题,提出一种水下图像复原方法。简化Jaffe-McGlamery水下成像模型,将多种方法所得背景光结合融合策略精准估计背景光,引入红通道先验理论预估透射
率,结合水下成像模型获得初始复原图像。针对图像细节不突出问题,采用对比度受限自适应直方图均衡化算法
(CLAHE)进行图像增强。实验在公开数据集UIEB上进行,所提出算法与2种常用的水下图像复原算法比较,实验
结果表明,所提方法有效的提升了图像质量,改善了视觉效果,恢复出清晰真实的图像。

关键词


图像复原;背景光融合;红通道先验;对比度受限自适应直方图均衡化算法

全文:

PDF


参考


[1]周洋.基于特征融合的水下图像增强研究[D].北

京交通大学,2023.

[2]翁成航.基于深度学习的水下图像增强算法研究

[D].南京信息工程大学,2024.

[3]魏郭依哲,陈思遥,刘玉涛等.水下图像增强

和修复算法综述[J].计算机应用研究,2021,38(09):

2561-2569+2589.

[4]张心祎,谭耀,邢向磊.基于物理先验的深度特

征融合水下图像复原[J].智能系统学报,2023,18(06):

1185-1196.

[5]He K, Sun J, Tang X. Single Image Haze Removal

Using Dark Channelprior[J]. Ieee Transactions On Pattern

Analysis And Machine Intelligence, 2010, 33(12): 2341-2353.

[6]郑建华,杨高林,刘双印等.双背景光自适应融

合与透射图精准估计水下图像复原[J].农业工程学报,

2022,38(14):174-182.

[7]Carlevaris-Bianco N, Mohan A, Eustice R M. Initial

Results In Underwater Single Image Dehazing[C]// Oceans

2010 Mts/Ieee Seattle. Seattle, Wa:Ieee, 2010: 1-8.

[8]邓晶.水下图像增强方法综述[J].电视技术,2022,

46(12):4-7+13.Doi:10.16280/J.Videoe.2022.12.002.

[9]王德兴,杨钰锐,袁红春,等.结合特征融合与

物理校正的水下图像增强方法[J].液晶与显示,2023,38

(11):1554-1566.

[10]W.Luo, S.Duan And J.Zheng, "Underwater Image

Restoration And Enhancement Based On A Fusion Algorithm

With Color Balance, Contrast Optimization, And Histogram

Stretching," In Ieee Access, Vol. 9, Pp. 31792-31804, 2021.

[11]Mcglamery B L. A Computer Model For

Underwater Camera Systems[C]// Ocean Optics Vi.

International Society For Optics And Photonics, Monterey,

Ca, Usa: Spie Press, 1980, 208: 221-231.

[12]Jaffe J S. Computer Modeling And The Design Of

Optimal Underwater Imaging Systems[J].Ieee Journal Of

Oceanic Engineering,1990,15(2):101-111.

[13]张红,索霆锋,宋婉莹.基于结构纹理分解的矿

井图像增强方法[J].工矿自动化,2024,50(03):56-64.

[14]Gordon H R. Can The Lambert‐Beer Law Be

Applied To The Diffuse Attenuation Coefficient Of Ocean

Water?[J]. Limnology And Oceanography, 1989, 34(8):

1389-1409.

[15]刘玉珍,周天飞,林森.基于局部纹理特征检测

的水下光学图像复原算法[J].华中科技大学学报(自然科

学版),2023,51(09):103-109.

[16]王柯俨,黄诗芮,李云松.水下光学图像重建

方法研究进展[J].中国图象图形学报,2022,27(05):

1337-1358.

[17]Chongyi L ,Chunle G ,Wenqi R , Et Al. An

Underwater Image Enhancement Benchmark Dataset And

Beyond. [J]. Ieee Transactions On Image Processing : A

Publication Of The Ieee Signal Processing Society, 2019, 29

4376-4389.

[18]Drews Jr P,Do Nascimento E,Moraes F,Et

Al.Transmission Estimation In Underwater Single

Images[C]//Proceedings Of Ieee International Conference

On Computer Vision Workshops. Washington D. C.,Usa:Ieee

Press,2013:825-830.

[19]Fu X Y,Zhuang P X,Huang Y, Et Al.A Retinex -

Based Enhancing Approach For Single Underwater Image[C].

Ieee International Co Nference On Image Processing, 2014:

4572 - 4576.

[20]Yang M, Sowmya A. An Underwater Color Image

Quality Evaluation Metric[J]. Ieee Transactions On Image

Processing, 2015, 24(12): 6062-6071.




DOI: http://dx.doi.org/10.12361/2661-3506-06-02-133832

Refbacks

  • 当前没有refback。