1.桂林电子科技大学广西图像图形与智能处理重点实验室,广西桂林 541004
2.南昌航空大学,江西南昌 330063
[ "江泽涛 男, 1961年3月出生,江西九江人.桂林电子科技大学教授,博士生导师,主要从事图像处理、计算机视觉、信息安全方面的研究." ]
[ "钱 艺(通讯作者) 男, 1993年6月出生,山东淄博人.桂林电子科技大学硕士研究生,主要从事图像增强方面的研究.E‑mail:Qyizos@163.com" ]
收稿:2020-08-03,
修回:2021-01-15,
纸质出版:2021-11-25
移动端阅览
江泽涛,钱艺,伍旭等.一种基于ARD‑GAN的低照度图像增强方法[J].电子学报,2021,49(11):2160-2165.
JIANG Ze-tao,QIAN Yi,WU Xu,et al.Low‑Light Image Enhancement Method Based on ARD‑GAN[J].ACTA ELECTRONICA SINICA,2021,49(11):2160-2165.
江泽涛,钱艺,伍旭等.一种基于ARD‑GAN的低照度图像增强方法[J].电子学报,2021,49(11):2160-2165. DOI: 10.12263/DZXB.20200822.
JIANG Ze-tao,QIAN Yi,WU Xu,et al.Low‑Light Image Enhancement Method Based on ARD‑GAN[J].ACTA ELECTRONICA SINICA,2021,49(11):2160-2165. DOI: 10.12263/DZXB.20200822.
为解决低照度图像增强过程中噪声放大、细节不足以及色彩还原问题,本文提出一种基于注意力机制残差密集生成对抗网络(Attention Residual Dense‑Generative Adversarial Networks
ARD‑GAN)的低照度图像增强方法.首先
该方法在全局光照估计模块(Global Illumination Estimation Module
GIEM)中生成全局曝光注意力图,以引导后续模块更好地进行照度增强;其次,使用卷积残差模块(Convolution and Residual Module
CRM)和基于通道注意力的残差密集模块(Channel Attention Residual Dense Module
CARDM)分别提取浅层特征和深层特征,并将不同层次的特征融合以获取更好的细节信息;然后,在CARDM基础上将密集连接与批归一化相结合抑制噪声;最后改进了损失函数,使增强后图像色彩还原更好.实验表明,ARD‑GAN有与主流算法相比,在主观视觉和客观评价指标上均得到更好的效果.
In order to solve the problems of noise amplification
insufficient detail and color restoration in the process of low‑light image enhancement
this paper proposes a method of low‑light image enhancement based on attention residual dense‑generative adversarial networks (ARD‑GAN). Firstly
the method generates a global exposure attention map in the global illumination estimation module (GIEM) to guide the subsequent modules to enhance the illumination better; secondly
it adopts the convolution and residual module (CRM) and the channel attention residual dense module (CARDM) to extract shallow features and deep features respectively
and fuses different features of levels to obtain better detailed information; furthermore
based on the CARDM
the dense connection and batch normalization are combined to suppress noise. Finally
the improved loss function restores the enhanced image color better. Comprehensive experiments are conducted
which show that ARD‑GAN can significantly outperform mainstream algorithms in subjective vision and objective evaluation indicators.
Reza A M . Realization of the contrast limited adaptive histogram equalization (CLAHE) for real‑time image enhancement [J]. Journal of VLSI Signal Processing Systems for Signal , Image and Video Technology, 2004 , 38 ( 1 ): 35 - 44 .
Guo X , Li Y , Ling H . LIME: Low‑light image enhancement via illumination map estimation [J]. IEEE Transactions on image processing , 2017 , 26 ( 2 ): 982 - 993 .
Dong X , Wang G , Pang Y , et al . Fast efficient algorithm for enhancement of low lighting video [A]. 2011 IEEE International Conference on Multimedia and Expo [C]. USA : IEEE , 2011 . 1 - 6 .
Tao L , Zhu C , Xiang G , et al . LLCNN : A convolutional neural network for low‑light image enhancement[A]. 2017 IEEE Visual Communications and Image Processing (VCIP) [C]. USA : IEEE , 2017 . 1 - 4 .
Zhang K , Zuo W , Chen Y , et al . Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising [J]. IEEE Transactions on Image Processing , 2017 , 26 ( 7 ): 3142 - 3155 .
Zhang H , Goodfellow I , Metaxas D , et al . Self‑attention generative adversarial networks [EB/OL]. https: //arxiv.org/abs/1805.08318 https://arxiv.org/abs/1805.08318 , 2018 .
Zhang Y , Tian Y , Kong Y , et al . Residual dense network for image super‑resolution [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. USA : IEEE , 2018 . 2472 - 2481 .
Huang G , Liu Z , Van Der Maaten L , et al . Densely connected convolutional networks [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [C]. USA : IEEE , 2017 . 4700 - 4708 .
He K , Zhang X , Ren S , et al . Deep residual learning for image recognition [A]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [C]. USA : IEEE , 2016 . 770 - 778 .
Sandler M , Howard A , Zhu M , et al . Mobilenetv2 : Inverted residuals and linear bottlenecks[A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. USA : IEEE , 2018 . 4510 - 4520 .
江泽涛 , 覃露露 . 一种基于U‑Net生成对抗网络的低照度图像增强方法 [J]. 电子学报 , 2020 , 48 ( 2 ): 258 - 264 .
Jiang Z T , Qin L L . Low‑light image enhancement method based on U‑net generative adversarial network [J]. Acta Electronica Sinica , 2020 , 48 ( 2 ): 258 - 264 . (in Chinese)
Lv F , Lu F , Wu J , et al . MBLLEN: Low‑light image/video enhancement using CNNs [A]. BMVC 2018 [C]. UK , 2018 . 220 .
Mao X , Li Q , Xie H , et al . Least squares generative adversarial networks [A]. Proceedings of the IEEE International Conference on Computer Vision (ICCV) [C]. USA : IEEE , 2017 . 2794 - 2802 .
Wang W , Wei C , Yang W , et al . GLADNet : Low‑light enhancement network with global awareness[A]. 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) [C]. USA : IEEE , 2018 . 751 - 755 .
Shen L , Yue Z , Feng F , et al . Msr‑net: Low‑light image enhancement using deep convolutional network [J]. arXiv preprint arXiv: 1711.02488 , 2017 .
Loh Y P , Chan C S . Getting to know low‑light images with the exclusively dark dataset [J]. Computer Vision and Image Understanding , 2019 , 178 : 30 - 42 .
Cai J , Gu S , Zhang L . Learning a deep single image contrast enhancer from multi‑exposure images [J]. IEEE Transactions on Image Processing , 2018 , 27 ( 4 ): 2049 - 2062 .
Chen Z , Jiang T , Tian Y . Quality assessment for comparing image enhancement algorithms [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. USA : IEEE , 2014 . 3003 - 3010 .
0
浏览量
19
下载量
8
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621