浏览全部资源
扫码关注微信
1.南京邮电大学 电子与光学工程学院、微电子学院,江苏 南京 210023
2.南京邮电大学 自动化院,江苏 南京 210023
[ "陈 刚(1995-),男,江苏南京人,硕士研究生,研究方向是光电成像与图像处理。E-mail: 1219023223@njupt.edu.cn" ]
[ "喻春雨(1976-),女,辽宁沈阳人,副教授,2006年于南京理工大学获光学工程博士学位,2006~2008年在北京大学信息科学技术学院从事博士后工作,2014~2015年在宾夕法尼亚大学医学院访学。E-mail: yucy@njupt.edu.cn" ]
收稿日期:2021-01-06,
修回日期:2021-04-08,
纸质出版日期:2021-08-15
移动端阅览
陈刚,刘言,杨贺超等.低照度彩色图像的自适应亮度增强[J].光学精密工程,2021,29(08):1999-2007.
CHEN Gang,LIU Yan,YANG He-chao,et al.Adaptive brightness correction of dim-lightening color images[J].Optics and Precision Engineering,2021,29(08):1999-2007.
陈刚,刘言,杨贺超等.低照度彩色图像的自适应亮度增强[J].光学精密工程,2021,29(08):1999-2007. DOI: 10.37188/OPE.20212908.1999.
CHEN Gang,LIU Yan,YANG He-chao,et al.Adaptive brightness correction of dim-lightening color images[J].Optics and Precision Engineering,2021,29(08):1999-2007. DOI: 10.37188/OPE.20212908.1999.
为恢复低照度场景图像的原有色彩信息和细节信息,本研究提出自适应亮度调节的低照度彩色图像增强方法。该方法首先对低照度场景连续拍摄多帧图像,并对其进行自适应伽马亮度校正;然后将多帧亮度校正后图像转换到YUV色彩空间并行两种处理,一种是提取Y通道分量分组进行基于权值调整二阶盲辨识的盲源分离降噪,一种是进行帧平均后提取Y通道分量与多个盲源分离降噪的Y通道分量依次进行结构匹配,并选出匹配最佳Y通道分量;再将最佳Y通道分量进行基于皮尔生长曲线的亮度调整后与经帧平均处理的U、V通道分量重新组合;最后将重组图像转换回RGB空间,即可得到视觉效果显著提升的彩色图像。本文提出的图像增强方法满足实时处理要求,可将原彩色图像的极低亮度提高54.4倍、中等亮度提高3.5倍;并将图像信息熵提高1.3~2.9倍。与典型的图像增强算法相比,本文提出的方法对低照度彩色图像在降低噪声、均衡光照和恢复细节方面有较大改善。
To improve the imaging performance in dim-lighting scenes, we propose adaptive brightness correction of dim-lighting color images. First, frame-averaging and Gamma correction are performed on a sequence of images. Second, the processed images are grouped before the following parallel processing steps are performed. In one of these steps, the images are converted into the YUV color space, and then, based on blind source separation (BSS), noise is removed from Y-channel components group by group; in another step, the best BSS-denoised Y-channel component is selected by matching with the frame-averaged Y-channel. Third, the best Y-channel component is adjusted based on the peel growth curve and then recombined with the averaged U-channel and V-channel components. Finally, the recombined image is converted back to the RGB color space. Experiment results show that the proposed image enhancement algorithm could increase the brightness of the low-luminosity image by 3.5-54.4 times and increase the information entropy by 1.3-2.9 times. The proposed algorithm outperforms the classical image enhancement algorithms in terms of noise reduction, brightness balancing, and color information restoration.
汪子君 , 罗渊贻 , 蒋尚志 , 等 . 基于引导滤波的自适应红外图像增强改进算法 [J]. 光谱学与光谱分析 , 2020 , 40 ( 11 ): 3463 - 3467 .
WANG Z J , LUO Y Y , JIANG SH Z , et al . Adaptive improved infrared image enhancement algorithm based on guided filtering [J]. Spectroscopy and spectral analysis , 2020 , 40 ( 11 ): 3463 - 3467 . (in Chinese)
ZUIDERVELD K . Contrast Limited Adaptive Histogram Equalization [J]. Graphics Gems , 1994 : 474 - 485 .
LI M D , LIU J Y , YANG W H , et al . Structure-revealing low-light image enhancement via robust retinex model [J]. IEEE Transactions on Image processing , 2018 , 27 ( 6 ) : 2828 - 2841 .
DONG X , WANG G , PANG Y , et al . Fast efficient algorithm for enhancement of low lighting video [C]. 2011 IEEE International Conference on Multimedia and Expo. IEEE , 2011 : 1 - 6 .
GUO X , LI Y , LING H . LIME: Low-light image enhancement via illumination map estimation [J]. IEEE Transactions on image processing , 2016 , 26 ( 2 ): 982 - 993 .
刘志成 , 王殿伟 , 刘颖 , 等 . 基于二维伽马函数的光照不均匀图像自适应校正算法 [J]. 北京理工大学学报 , 2016 , 36 ( 2 ): 191 - 196+214 .
LIU ZH CH , WANG D W , LIU Y , et al . Adaptive correction algorithm for uneven illumination image based on two-dimensional gamma function [J]. Journal of Beijing University of technology , 2016 , ( 2 ): 191 - 196+214 . (in Chinese)
ZOHAIR A . Nighttime image enhancement using a new illumination boost algorithm [J]. IET Image Processing , 2019 , 13 ( 8 ) : 1314 - 1320 .
YEREDOR A . Blind separation of Gaussian sources via second-order statistics with asymptotically optimal weighting [J]. IEEE Signal Processing Letters , 2000 , 7 ( 7 ): 197 - 200 .
李华夏 . 趋势预测及其应用 [J]. 职大学报 , 2001 ,( 2 ): 9 - 10+78 .
LI H Y . Trend prediction and its Application [J]. Journal of Vocational University , 2001 ,( 2 ): 9 - 10+78 . (in Chinese)
田会娟 , 蔡敏鹏 , 关涛 , 等 . 基于YCbCr颜色空间的Retinex低照度图像增强方法研究 [J]. 光子学报 , 2020 , 49 ( 02 ): 173 - 184 .
TIAN H J , CAI M P , GUANN TAO , et al . Research on Retinex Low-illumination Image Enhancement Based on YCbCr color space [J]. Acta Photonica Sinica , 2020 , 49 ( 2 ): 173 - 184 . (in Chinese)
沈帆 , 李翰林 , 孙斌 , 等 . 基于Anscombe变换的X射线图像序列盲源分离降噪 [J]. 光学 精密工程 , 2020 , 28 ( 1 ): 244 - 250 .
SHEN F , LI H L , SUN B , et al . Blind source separation and noise reduction of X-ray image sequences based on Anscombe transform [J]. Opt. Precision Eng. , 2020 , 28 ( 1 ): 244 - 250 . (in Chinese)
刘邦 , 肖涵 , 易灿灿 . 基于核函数的二阶盲辨识的单通道信号盲分离方法研究 [J]. 机械强度 , 2018 , 40 ( 5 ): 1043 - 1049 .
LIU B , XIAO H , YI C C . Blind separation method of single channel signal based on second-order blind identification based on kernel function [J]. Mechanical strength , 2018 , 40 ( 5 ): 1043 - 1049 . (in Chinese)
WANG J J , CHEN P , ZHENNG N N , et al . Associations between MSE and SSIM as cost functns in linear decomposition with application to bit allocation for sparse coding [J]. Neurocomputing , 2021 , 422 : 139 - 149 .
JIN-SAN K , KI-DOO K . Dynamic Range Enhancement Using New MSF Image and CLAHE . 2020 , 45 ( 2 ): 264 - 273 .
李郁峰 , 蒋勇 , 陈念年 , 等 . RGB颜色空间的夜视图像彩色融合 [J]. 光学 精密工程 , 2018 , 26 ( 11 ): 2795 - 2804 .
LI Y F , JIANG Y , CHEN N N , et al .. Color Fusion of Night Vision Images under RGB Color Space [J]. Opt. Precision Eng. , 2018 , 26 ( 11 ): 2795 - 2804 . (in Chinese)
MITTAL A , MOORTHY A K , BOVIK A C . No-reference image quality assessment in the spatial domain [J]. IEEE Transactions on image processing , 2012 , 21 ( 12 ): 4695 - 4708 .
0
浏览量
1475
下载量
6
CSCD
关联资源
相关文章
相关作者
相关机构