浏览全部资源
扫码关注微信
四川大学 电气工程学院,四川 成都 610065
Received:25 May 2022,
Revised:23 August 2022,
Published:25 April 2023
移动端阅览
石吉豪,钟羽中,郑秀娟等.基于光线散射衰减模型的低照度图像增强[J].光学精密工程,2023,31(08):1244-1255.
SHI Jihao,ZHONG Yuzhong,ZHENG Xiujuan,et al.Low-light image enhancement algorithm based on light scattering attenuation model[J].Optics and Precision Engineering,2023,31(08):1244-1255.
石吉豪,钟羽中,郑秀娟等.基于光线散射衰减模型的低照度图像增强[J].光学精密工程,2023,31(08):1244-1255. DOI: 10.37188/OPE.20233108.1244.
SHI Jihao,ZHONG Yuzhong,ZHENG Xiujuan,et al.Low-light image enhancement algorithm based on light scattering attenuation model[J].Optics and Precision Engineering,2023,31(08):1244-1255. DOI: 10.37188/OPE.20233108.1244.
针对传统图像增强算法在总体照度低且光照分布不均的环境内易造成图像过度增强和自然度保存能力弱的问题,提出了一种基于光线散射衰减模型的低照度图像增强算法。首先,本文提出了光线散射衰减模型,该模型合理解释了非均匀光照分布的成像过程,其次,通过Max-RGB滤波器分别估计每个像素的照度,初始化照明图,然后,根据光照随图像分割区域入射角、入射距离平滑衰减的特性,利用深度信息和梯度信息优化光照分量,获得精确照明图;此外,利用暗通道先验中的透射率所具有的局部相似性来约束反射分量估计;最后,通过提出的光线散射衰减模型融合优化光照分量和反射分量,获得最终的低照度增强图像。通过与NPE,LIME,HE,ALSM,MSRCR,MF,WV_SIRE算法比较,在不同场景的低照度图像上,无参考各向异性质量评估器(BIQAA)最大为0.019 6,模糊检测累积概率(CPBD)最大为0.680 1,无参考空间域图像质量评估器(BRISQUE)最小为21.471 5,自然图像质量评估器(NIQE)最小为2.699 5,综合性能优于其他对比算法。实验结果表明,本文算法能够有效抑制噪声,提高图像对比度和亮度,更好地保留图像自然度。
To address the problems of the over-enhancement and weak naturalness preservation ability of images in low-light environments with uneven illumination distribution, this study proposes a low-light image enhancement method based on the light-scattering attenuation model. First, a light-scattering attenuation model, which can explain the imaging process of non-uniform illumination distribution, is introduced. Second, the illumination map is initialized by estimating the illumination of each pixel using the Max-RGB filter. Third, according to the smooth attenuation characteristics of the illumination considering the incident distance between the segmented image areas, illumination components are optimized based on the depth and gradient data to obtain an accurate illumination map. Furthermore, constrain the estimation of the reflection component based on the local similarity possessed by the dark channel prior to transmittance. Finally, the low-light enhanced image is obtained by fusing the optimized illumination and reflection components using the proposed light-scattering attenuation model. The proposed method performs better than the NPE, LIME, HE, ALSM, MSRCR, MF, and WV_SIRE algorithms. In the case of the low-light image in different scenarios, a blind image quality assessment via anisotropy yielded values of up to 0.019 6 and cumulative probability of blur detection yielded values of up to 0.680 1 and the referenceless image spatial quality and natural image quality evaluators yielded minimum values of 21.471 5 and 2.699 5, respectively. The overall performance of the proposed method is better than those of the other algorithms. The experimental results confirm that the proposed method can effectively suppress noise, enhance image contrast and brightness, and well preserve image naturalness.
JAVED S , MAHMOOD A , DIAS J , et al . Robust structural low-rank tracking [J]. IEEE Transactions on Image Processing , 2020 , 29 : 4390 - 4405 . doi: 10.1109/tip.2020.2972102 http://dx.doi.org/10.1109/tip.2020.2972102
王殿伟 , 邢质斌 , 韩鹏飞 , 等 . 基于模拟多曝光融合的低照度全景图像增强 [J]. 光学 精密工程 , 2021 , 29 ( 2 ): 349 - 362 . doi: 10.37188/OPE.20212902.0349 http://dx.doi.org/10.37188/OPE.20212902.0349
WANG D W , XING Z B , HAN P F , et al . Low illumination panoramic image enhancement algorithm based on simulated multi-exposure fusion [J]. Opt. Precision Eng. , 2021 , 29 ( 2 ): 349 - 362 . (in Chinese) . doi: 10.37188/OPE.20212902.0349 http://dx.doi.org/10.37188/OPE.20212902.0349
苑玮琦 , 薛丹 . 基于机器视觉的隧道衬砌裂缝检测算法综述 [J]. 仪器仪表学报 , 2017 , 38 ( 12 ): 3100 - 3111 .
YUAN W Q , XUE D . Review of tunnel lining crack detection algorithm based on machine vision [J]. Chinese Journal of Scientific Instrument , 2017 , 38 ( 12 ): 3100 - 3111 . (in Chinese)
WEI X , ZHANG X , WANG S , et al . DA-DRN : Degradation-Aware Deep Retinex Network for Low-Light Image Enhancement [EB/OL]. 2021 : arXiv : 2110 . 01809 . https://arxiv.org/abs/2110.01809 https://arxiv.org/abs/2110.01809
LORE K G , AKINTAYO A , SARKAR S . LLNet : A Deep Autoencoder Approach to Natural Low-Light Image Enhancement [EB/OL]. 2015 : arXiv : 1511 . 03995 . https://arxiv.org/abs/1511.03995 https://arxiv.org/abs/1511.03995
SAAD N H , ISA N A M , SALEH H M . Nonlinear exposure intensity based modification histogram equalization for non-uniform illumination image enhancement [J]. IEEE Access , 2021 , 9 : 93033 - 93061 . doi: 10.1109/access.2021.3092643 http://dx.doi.org/10.1109/access.2021.3092643
黄慧 , 董林鹭 , 刘小芳 , 等 . 改进Retinex的低光照图像增强 [J]. 光学 精密工程 , 2020 , 28 ( 8 ): 1835 - 1849 .
HUANG H , DONG L L , LIU X F , et al . Improved retinex low light image enhancement method [J]. Opt. Precision Eng. , 2020 , 28 ( 8 ): 1835 - 1849 . (in Chinese)
JOBSON D J , RAHMAN Z , WOODELL G A . Properties and performance of a center/surround retinex [J]. IEEE Transactions on Image Processing , 1997 , 6 ( 3 ): 451 - 462 . doi: 10.1109/83.557356 http://dx.doi.org/10.1109/83.557356
ZHU D , CHEN G N , MICHELINI P N , et al . Fast Image Enhancement Based on Maximum and Guided Filters [C]. 2019 IEEE International Conference on Image Processing (ICIP). 2225,2019 , Taipei, China. IEEE , 2019 : 4080 - 4084 . doi: 10.1109/icip.2019.8803591 http://dx.doi.org/10.1109/icip.2019.8803591
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 ( 8 ): 1999 - 2007 . doi: 10.37188/OPE.20212908.1999 http://dx.doi.org/10.37188/OPE.20212908.1999
CHEN G , LIU Y , YANG H CH , et al . Adaptive brightness correction of dim-lightening color images [J]. Opt. Precision Eng. , 2021 , 29 ( 8 ): 1999 - 2007 . (in Chinese) . doi: 10.37188/OPE.20212908.1999 http://dx.doi.org/10.37188/OPE.20212908.1999
FU X Y , ZENG D L , HUANG Y , et al . A fusion-based enhancing method for weakly illuminated images [J]. Signal Processing , 2016 , 129 ( C ): 82 - 96 . doi: 10.1016/j.sigpro.2016.05.031 http://dx.doi.org/10.1016/j.sigpro.2016.05.031
GAO Y Y , HU H M , LI B , et al . Naturalness preserved nonuniform illumination estimation for image enhancement based on retinex [J]. IEEE Transactions on Multimedia , 2017 , 20 : 335 - 344 . doi: 10.1109/tmm.2017.2740025 http://dx.doi.org/10.1109/tmm.2017.2740025
WANG S H , ZHENG J , HU H M , et al . Naturalness preserved enhancement algorithm for non-uniform illumination images [J]. IEEE Transactions on Image Processing , 2013 , 22 ( 9 ): 3538 - 3548 . doi: 10.1109/tip.2013.2261309 http://dx.doi.org/10.1109/tip.2013.2261309
FU X Y , ZENG D L , YUE H , et al . A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation [C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE , 2016 : 2782 - 2790 . doi: 10.1109/cvpr.2016.304 http://dx.doi.org/10.1109/cvpr.2016.304
GUO X Y , LI Y , LING H B , et al . LIME: Low-Light Image Enhancement via Illumination Map Estimation [J]. IEEE Transactions on Image Processing , 2016 , 26 ( 2 ): 982 - 993 . doi: 10.1109/tip.2016.2639450 http://dx.doi.org/10.1109/tip.2016.2639450
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 . doi: 10.1109/tip.2018.2810539 http://dx.doi.org/10.1109/tip.2018.2810539
WANG Y F , LIU H M , FU Z W . Low-light image enhancement via the absorption light scattering model [J]. IEEE Transactions on Image Processing , 2019 , 28 ( 11 ): 5679 - 5690 . doi: 10.1109/tip.2019.2922106 http://dx.doi.org/10.1109/tip.2019.2922106
KOKUL T , ANPARASY S . Single image defogging using depth estimation and scene-specific dark channel prior [C]. 2020 20th International Conference on Advances in ICT for Emerging Regions (ICTer). 47,2020 , Colombo, Sri Lanka. IEEE , 2021 : 190 - 195 . doi: 10.1109/icter51097.2020.9325450 http://dx.doi.org/10.1109/icter51097.2020.9325450
LI Z G , ZHENG J H . Edge-preserving decomposition-based single image haze removal [J]. IEEE Transactions on Image Processing , 2015 , 24 ( 12 ): 5432 - 5441 . doi: 10.1109/tip.2015.2482903 http://dx.doi.org/10.1109/tip.2015.2482903
BARRON JONATHAN T , JITENDRA M . Shape, illumination, and reflectance from shading [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015 , 37 ( 8 ): 1670 - 87 . doi: 10.1109/tpami.2014.2377712 http://dx.doi.org/10.1109/tpami.2014.2377712
FU X Y , LIAO Y H , ZENG D L , et al . A probabilistic method for image enhancement with simultaneous illumination and reflectance estimation [J]. IEEE Transactions on Image Processing , 2015 , 24 ( 12 ): 4965 - 4977 . doi: 10.1109/tip.2015.2474701 http://dx.doi.org/10.1109/tip.2015.2474701
TELEA A . An image inpainting technique based on the fast marching method [J]. Journal of Graphics Tools , 2004 , 9 ( 1 ): 23 - 34 . doi: 10.1080/10867651.2004.10487596 http://dx.doi.org/10.1080/10867651.2004.10487596
HU H M , GUO Q , ZHENG J , et al . Single image defogging based on illumination decomposition for visual maritime surveillance [J]. IEEE Transactions on Image Processing , 2019 , 28 ( 6 ): 2882 - 2897 . doi: 10.1109/tip.2019.2891901 http://dx.doi.org/10.1109/tip.2019.2891901
GABARDA S , CRISTÓBAL G . Blind image quality assessment through anisotropy [J]. Journal of the Optical Society of America A , 2007 , 24 ( 12 ): B42 . doi: 10.1364/josaa.24.000b42 http://dx.doi.org/10.1364/josaa.24.000b42
NARVEKAR N D , KARAM L J . A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection [C]. 2009 International Workshop on Quality of Multimedia Experience . 2931,2009 , San Diego, CA, USA . IEEE , 2009 : 87 - 91 . doi: 10.1109/qomex.2009.5246972 http://dx.doi.org/10.1109/qomex.2009.5246972
MITTAL A , MOORTHY A K , BOVIK A C . Blind/Referenceless image spatial quality evaluator [C]. 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR). 69,2011 , Pacific Grove, CA, USA. IEEE , 2012 : 723 - 727 . doi: 10.1109/acssc.2011.6190099 http://dx.doi.org/10.1109/acssc.2011.6190099
MITTAL A , SOUNDARARAJAN R , BOVIK A C . Making a “completely blind” image quality analyzer [J]. IEEE Signal Processing Letters , 2013 , 20 ( 3 ): 209 - 212 . doi: 10.1109/lsp.2012.2227726 http://dx.doi.org/10.1109/lsp.2012.2227726
0
Views
502
下载量
1
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution