基于物理模型的低照度图像增强算法

doi:10.11772/j.issn.1001-9081.2015.08.2301

计算机应用 ›› 2015, Vol. 35 ›› Issue (8): 2301-2304.DOI: 10.11772/j.issn.1001-9081.2015.08.2301

基于物理模型的低照度图像增强算法

王小元^1,2, 张红英^1,2, 吴亚东³, 刘言^1,2

1. 西南科技大学信息工程学院, 四川绵阳 621010;
2. 特殊环境机器人技术四川省重点实验室(西南科技大学), 四川绵阳 621010;
3. 西南科技大学计算机科学与技术学院, 四川绵阳 621010

收稿日期:2015-03-01 修回日期:2015-04-19 出版日期:2015-08-10 发布日期:2015-08-14
通讯作者: 张红英(1976-),女,四川德阳人,教授,博士,主要研究方向:图像分析与处理、运动目标检测与跟踪,zhy0838@163.com
作者简介:王小元(1989-),女,山西大同人,硕士研究生,主要研究方向:图像处理、模式识别; 吴亚东(1979-),男,河南舞阳人,教授,博士,CCF会员,主要研究方向:图像处理及可视化; 刘言(1987-),男,四川广安人,硕士研究生,主要研究方向:图像处理。
基金资助:
中国科学院西部之光人才培养计划项目(科发人教字(2012)179号);特殊环境机器人技术四川省重点实验室开放基金资助项目(13zxtk05)。

Low-illumination image enhancement based on physical model

WANG Xiaoyuan^1,2, ZHANG Hongying^1,2, WU Yadong³, LIU Yan^1,2

1. School of Information Engineering, Southwest University of Science and Technology, Mianyang Sichuan 621010, China;
2. Robot Technology Used for Special Environment Key Laboratory of Sichuan Province (Southwest University of Science and Technology), Mianyang Sichuan 621010, China;
3. School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang Sichuan 621010, China

Received:2015-03-01 Revised:2015-04-19 Online:2015-08-10 Published:2015-08-14

摘要/Abstract

摘要：

针对低照度图像反转后为与雾天图像相似的伪雾图,其雾的浓度由光照情况而非景深决定这一特点,提出一种基于物理模型的低照度图像增强算法。该算法根据光照情况给出一种更加准确且快速的新方法估计伪雾图的透射率。首先,采用暗原色先验规律对伪雾图的环境光值进行估计,并基于光照情况对透射率进行估计;然后,基于大气散射模型还原出无雾图像;最后,对无雾图像反转得到低照度图像的增强结果,并对该结果进行细节补偿得到最终的增强图像。大量实验表明,与基于暗原色先验的增强算法、基于去雾技术的增强算法及带色彩恢复的多尺度Retinex算法相比,该算法处理效率更高且效果良好,信息不会丢失,可有效提高图像分析识别等系统的工作效率。

关键词: 低照度, 图像增强, 大气散射模型, 去雾, 暗原色先验

Abstract:

Since a low-illumination image will become a pseudo fog map after inversion, and the concentration of this pseudo fog map is decided by illumination rather than depth of field, a low-illumination image enhancement method based on physical model was proposed, which provided a fast and accurate method to estimate the transmittance. Firstly, dark channel prior was used to estimate atmospheric light value of pseudo fog map and the transmittance was estimated according to the illumination. Secondly, the image without fog was restored based on the atmospheric scattering mode. Finally, the enhanced image was obtained by inversing the image without fog. Furthermore, the clear image was got by making detail compensation on the enhanced image. A large number of experiments show that the proposed algorithm is faster and performs well without losing information compared with the existing algorithms including the enhancement algorithms based on dark channel prior, defogging techniques and the multi-scale Retinex with color restoration, meanwhile it can improve the efficiency of image analysis and recognition system.

Key words: low-illumination, image enhancement, atmospheric scattering model, dehazing, dark channel prior

中图分类号:

TP391.413

王小元, 张红英, 吴亚东, 刘言. 基于物理模型的低照度图像增强算法[J]. 计算机应用, 2015, 35(8): 2301-2304.

WANG Xiaoyuan, ZHANG Hongying, WU Yadong, LIU Yan. Low-illumination image enhancement based on physical model[J]. Journal of Computer Applications, 2015, 35(8): 2301-2304.

参考文献

[1] HANG D. Details keeping histogram equalization approach of low-illumination video image [J]. Computer Simulation, 2013, 30(8): 233-236. (韩殿元.低照度下视频图像保细节直方图均衡化方法[J].计算机仿真,2013,30(8):233-236.)
[2] ZHOU Z, SANG N, HU X. Global brightness and local contrast adaptive enhancement for low illumination color image [J]. Optik, 2013, 125(6):1795-1799.
[3] XIAO J, SHAN S, DUAN P, et al. A fast image enhancement algorithm based on fusion of different color spaces [J]. Acta Automatica Sinica, 2014, 40(4):697-705. (肖进胜,单姗姗,段鹏飞,等.基于不同色彩空间融合的快速图像增强算法[J].自动化学报,2014,40(4):697-705.)
[4] AGAIAN S, ROOPAEI M. New haze removal scheme and novel measure of enhancement [C]//Proceeding of the 2013 IEEE International Conference on Cybernetics. Washington, DC: IEEE Computer Society, 2013:219-224.
[5] TAN R T. Visibility in bad weather from a single image [C]//CVPR 2008: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2008: 1-8.
[6] FATTAL R. Single image dehazing [J]. ACM Transactions on Graphics, 2008, 27(3): Article No. 72.
[7] XU H, GUO J, LIU Q, et al. Fast image dehazing using improved dark channel prior [C]//Proceeding of the 2012 IEEE International Conference on Information Science and Technology. Washington, DC: IEEE Computer Society, 2012: 663-667.
[8] ZHOU S, GENG N. Optimising dark channel prior-based single image haze removal technigue [J]. Computer Applications and Software, 2013, 30(7):287-289. (周首峰,耿楠.基于暗原色先验的单幅图像去雾方法的优化技术[J].计算机软件与应用,2013,30(7):287-289.)
[9] CHEN Z, SHEN J, ROTH P. Single image defogging algorithm based on dark channel priority [J]. Journal of Multimedia, 2013, 8(4): 432-438.
[10] DONG X, WANG G, PANG Y, et al. Fast efficient algorithm for enhancement of low lighting video [C]//ICME '11: Proceedings of the 2011 IEEE International Conference on Multimedia and Expo. Washington, DC: IEEE Computer Society, 2011: 1-6.
[11] LIU Y, PAN J, PANG Y. Low lighting video enhancement algorithm based on dark channel prior [J]. Electronic Measurement Technology, 2013, 36(10):55-58. (刘洋,潘静, 庞彦伟.一种基于暗原色先验的低照度视频增强算法[J].电子测量技术,2013,36(10):55-58.)
[12] ZHANG X, SHEN P, LUO L, et al. Enhancement and noise reduction of very low light level images [C]//ICPR 2012: Proceedings of the 21st International Conference on Pattern Recognition. Piscataway: IEEE, 2012: 2034-2037.
[13] HE K, SUN J, TANG X. Single image haze removal using dark channel prior [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.
[14] RAHMAN Z-U, JOBSON D J, WOODELL G A. Retinex processing for automatic image enhancement [J]. Journal of Electronic Imaging, 2004, 13(1): 100-110.
[15] HE K, SUN J, TANG X. Guide image filtering [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1-13.

基于物理模型的低照度图像增强算法

Low-illumination image enhancement based on physical model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	孙潇, 徐金东. 基于级联生成对抗网络的遥感图像去雾方法[J]. 计算机应用, 2021, 41(8): 2440-2444.
[2]	牛康力, 谌雨章, 沈君凤, 曾张帆, 潘永才, 王绎冲. 基于深度学习的双通道夜视图像复原方法[J]. 计算机应用, 2021, 41(6): 1775-1784.
[3]	贺杰安, 吴晓红, 何小海, 胡建蓉, 卿粼波. 结合图像增强和卷积神经网络的小麦不完善粒识别[J]. 计算机应用, 2021, 41(3): 911-916.
[4]	杨佳义, 陈勇. 低照度视频图像自适应补偿增强的设计与实现[J]. 计算机应用, 2020, 40(8): 2372-2377.
[5]	于天河, 李昱祚, 兰朝凤. 基于顶帽底帽变换的仿生图像增强算法[J]. 计算机应用, 2020, 40(5): 1440-1445.
[6]	王瑞尧, 岳雪亭, 周志青, 耿则勋. 最大差值图决策的低照度图像自适应增强算法[J]. 计算机应用, 2020, 40(4): 1164-1170.
[7]	王云飞, 王园宇. 基于Msmall-Patch训练的夜晚单幅图像去雾算法——MP-CGAN[J]. 计算机应用, 2020, 40(3): 865-871.
[8]	邓天民, 方芳, 周臻浩. 基于改进空间金字塔池化卷积神经网络的交通标志识别[J]. 计算机应用, 2020, 40(10): 2872-2880.
[9]	司马紫菱, 胡峰. 基于模拟多曝光融合的低照度图像增强方法[J]. 计算机应用, 2019, 39(6): 1804-1809.
[10]	程宇, 邓德祥, 颜佳, 范赐恩. 基于卷积神经网络的弱光照图像增强算法[J]. 计算机应用, 2019, 39(4): 1162-1169.
[11]	娄梦莹, 袁丽莎, 刘娅琴, 万雪梅, 杨丰. 基于自适应融合的手掌静脉增强方法[J]. 计算机应用, 2019, 39(4): 1176-1182.
[12]	周冲, 刘欢, 赵爱玲, 张鹏程, 刘祎, 桂志国. 基于梯度场的工业X射线图像增强算法[J]. 计算机应用, 2019, 39(10): 3088-3092.
[13]	李红, 王瑞尧, 耿则勋, 胡海峰. 基于多尺度梯度域引导滤波的低照度图像增强算法[J]. 计算机应用, 2019, 39(10): 3046-3052.
[14]	梁中豪, 彭德巍, 金彦旭, 郭梁. 基于交通场景区域增强的单幅图像去雾方法[J]. 计算机应用, 2018, 38(5): 1420-1426.
[15]	雷思佳, 赵凤群. 基于自适应Riesz分数阶微分的雾天图像增强[J]. 计算机应用, 2018, 38(5): 1427-1431.