Low-light level image enhancement algorithm based on double-branch pyramid model

Qing-jiang CHEN; Yuan GU; Jin-yang LI

doi:10.37188/CJLCD.2021-0221

您当前的位置：

首页 >

文章列表页 >

Low-light level image enhancement algorithm based on double-branch pyramid model

Image Processing | 更新时间：2022-03-25

- Low-light level image enhancement algorithm based on double-branch pyramid model
- Chinese Journal of Liquid Crystals and Displays Vol. 37, Issue 3, Pages: 395-404(2022)
- 作者机构：
  
  西安建筑科技大学理学院，陕西西安 710055
- 作者简介：
- 基金信息：
  
  National Natural Science Foundatim of China(61902304)
- DOI：10.37188/CJLCD.2021-0221
  CLC： TP391.4
- Received：25 August 2021，
  
  Revised：04 October 2021，
  
  Published：2022-03
- 稿件说明：
移动端阅览
Qing-jiang CHEN, Yuan GU, Jin-yang LI. Low-light level image enhancement algorithm based on double-branch pyramid model[J]. Chinese journal of liquid crystals and displays, 2022, 37(3): 395-404.
DOI：

Qing-jiang CHEN, Yuan GU, Jin-yang LI. Low-light level image enhancement algorithm based on double-branch pyramid model[J]. Chinese journal of liquid crystals and displays, 2022, 37(3): 395-404. DOI： 10.37188/CJLCD.2021-0221.

摘要

针对微光图像存在亮度低、细节丢失严重以及现有算法增强后的微光图像存在曝光过度、颜色失真等问题，提出双分支金字塔网络的微光图像增强算法。首先，将微光图像从RGB颜色空间转换到HSV颜色空间。其次，对

分量采用双分支金字塔网络的微光图像增强算法，自适应获取图像特征。网络结构由并行双分支构成，含层级残差模块的分支有效增强

分量亮度，含特征金字塔注意力模块的分支获取深层特征信息。最后，对双分支结构提取的信息进行融合，并将增强后的图像从HSV颜色空间转换回RGB颜色空间。所提算法在真实图像上的峰值信噪比及结构相似度的均值分别达到29.451 dB和0.930 1，均高于其他对比算法。实验结果表明，所提算法对

分量进行增强提高了图像亮度，有效地恢复了图像细节。

Abstract

A low light level image enhancement algorithm based on double branch pyramid model is proposed. It is used to solve the problems of low brightness

serious loss of detail

over exposure and color distortion of the low light level image enhanced by existing algorithms. Firstly

the low-light level image is converted from RGB color space to HSV color space. Secondly

the low-light level image enhancement network of double branching pyramid network is constructed for the

component

and the image features are obtained adaptively. The network structure is composed of two parallel branches. The branch with hierarchical residual module can effectively enhance the brightness of

component

and the branch with feature pyramid attention module can obtain deep feature information. Finally

the information extracted from the dual-branch structure is fused

and the enhanced image is converted from HSV color space to RGB color space. The peak signal-to-noise ratio and the average structure similarity of the proposed algorithm on real images are 29.451 dB and 0.930 1 respectively

which are higher than other comparison algorithms. Experimental results show that the enhancement of the

component can effectively improve the image brightness and restore the image details.

关键词

Keywords

references

R HUMMEL . Image enhancement by histogram transformation . Computer Graphics and Image Processing , 1977 . 6 ( 2 ): 184 - 195 . .

S M PIZER , E P AMBURN , J D AUSTIN , 等 . Adaptive histogram equalization and its variations . Computer Vision, Graphics, and Image Processing , 1987 . 39 ( 3 ): 355 - 368 . DOI: 10.1016/S0734-189X(87)80186-X http://doi.org/10.1016/S0734-189X(87)80186-X .

E H LAND . The retinex theory of color vision . Scientific American , 1977 . 237 ( 6 ): 108 - 128 . .

D J JOBSON , Z RAHMAN , G A WOODELL . Properties and performance of a center/surround retinex . IEEE Transactions on Image Processing , 1997 . 6 ( 3 ): 451 - 462 . DOI: 10.1109/83.557356 http://doi.org/10.1109/83.557356 .

林剑萍 , 廖一鹏 . 结合分数阶微分及Retinex的NSCT自适应低照度图像增强 . 液晶与显示 , 2020 . 35 ( 4 ): 360 - 373 . DOI: 10.3788/YJYXS20203504.0360 http://doi.org/10.3788/YJYXS20203504.0360 .

J P LIN , Y P LIAO . NSCT adaptive low illumination image enhancement combining fractional differential and Retinex . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 4 ): 360 - 373 . DOI: 10.3788/YJYXS20203504.0360 http://doi.org/10.3788/YJYXS20203504.0360 .

X J GUO , Y Li , H B LING . LIME: low-light image enhancement via illumination map estimation . IEEE Transactions on Image Processing , 2017 . 26 ( 2 ): 982 - 993 . DOI: 10.1109/TIP.2016.2639450 http://doi.org/10.1109/TIP.2016.2639450 .

S SINGH , D GUPTA . Detail enhanced feature-level medical image fusion in decorrelating decomposition domain . IEEE Transactions on Instrumentation and Measurement , 2020 . 70 4502009 DOI: 10.1109/TIM.2020.3038603 http://doi.org/10.1109/TIM.2020.3038603 .

TAO L, ZHU C, XIANG G Q, et al . LLCNN: a convolutional neural network for low-light image enhancement [C]. Proceedings of 2017 IEEE Visual Communications and Image Processing ( VCIP ). St. Petersburg: IEEE, 2017: 1-4.

C Y LI , J C GUO , F PORIKLI , 等 . LightenNet: a convolutional neural network for weakly illuminated image enhancement . Pattern Recognition Letters , 2018 . 104 15 - 22 . DOI: 10.1016/j.patrec.2018.01.010 http://doi.org/10.1016/j.patrec.2018.01.010 .

Y F JIANG , X Y GONG , D LIU , 等 . EnlightenGAN: deep light enhancement without paired supervision . IEEE Transactions on Image Processing , 2021 . 30 2340 - 2349 . DOI: 10.48550/arXiv.1906.06972 http://doi.org/10.48550/arXiv.1906.06972 .

K M HE , J SUN , X O TANG . Single image haze removal using dark channel prior . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2011 . 33 ( 12 ): 2341 - 2353 . DOI: 10.1109/TPAMI.2010.168 http://doi.org/10.1109/TPAMI.2010.168 .

LI H C, XIONG P F, AN J, et al . Pyramid attention network for semantic segmentation [J]. arXiv : 1805.10180, 2018.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [J]. arXiv : 1409.1556, 2015.

YING Z Q, LI G, GAO W. A bio-inspired multi-exposure fusion framework for low-light image enhancement [J]. arXiv: 1711.00591, 2017.

CHEN X Y, WANG S A. Superpixel segmentation based on Delaunay triangulation [C]// Proceedings of the 23 rd International Conference on Mechatronics and Machine Vision in Practice ( M2VIP ). Nanjing, China: IEEE, 2016: 1-6.

J MANNOS , D SAKRISON . The effects of a visual fidelity criterion of the encoding of images . IEEE Transactions on Information Theory , 1974 . 20 ( 4 ): 525 - 536 . DOI: 10.1109/TIT.1974.1055250 http://doi.org/10.1109/TIT.1974.1055250 .

Z WANG , A C BOVIK , H R SHEIKH , 等 . Image quality assessment: from error visibility to structural similarity . IEEE Transactions on Image Processing , 2004 . 13 ( 4 ): 600 - 612 . DOI: 10.1109/tip.2003.819861 http://doi.org/10.1109/tip.2003.819861 .

CHEN C, CHEN Q F, XU J, et al . Learning to see in the dark [C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City: IEEE, 2018: 3291-3300.

LEE C, LEE C, KIM C S. Contrast enhancement based on layered difference representation [C]// Proceedings of the 19th IEEE International Conference on Image Processing . Orlando: IEEE, 2012: 965-968.

谢小甫 , 周进 , 吴钦章 . 一种针对图像模糊的无参考质量评价指标 . 计算机应用 , 2010 . 30 ( 4 ): 921 - 924 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201004022.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201004022.htm , .

X F XIE , J ZHOU , Q Z WU . No-reference quality index for image blur . Journal of Computer Applications , 2010 . 30 ( 4 ): 921 - 924 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201004022.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201004022.htm , .

Views

108

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Design of heterogeneous FPGA hardware accelerator based on CNN

Lightweight image super-resolution combining residual learning and layer attention

Remote sensing image change detection based on CNN-Transformer structure

Wavefront correction method based on P-U-net for pyramid wavefront detector

Image rain removal algorithm based on multi-cascade progressive convolution structure

Related Author

JI Haolin

XU Wei

PIAO Yongjie

WU Xiaobin

GAO Tan

WU Difan

ZHANG Xuande

PAN Mengyang

Related Institution

Key Laboratory of Space-based Dynamic & Rapid Optical Imaging Technology， Chinese Academy of Sciences

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

University of Chinese Academy of Sciences

School of Electronic Information and Artificial Intelligence， Shaanxi University of Science & Technology， Xi′an

College of Science， Jiangnan University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰