低照度环境下视频增强技术

朴燕; 刘磊; 刘笑宇

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

低照度环境下视频增强技术

朴燕, 刘磊, 刘笑宇

文章导航 > 红外与激光工程 > 2014 > 43(6): 2021-2026

朴燕, 刘磊, 刘笑宇. 低照度环境下视频增强技术[J]. 红外与激光工程, 2014, 43(6): 2021-2026.

引用本文:

朴燕, 刘磊, 刘笑宇. 低照度环境下视频增强技术[J]. 红外与激光工程, 2014, 43(6): 2021-2026.

Piao Yan, Liu Lei, Liu Xiaoyu. Enhancement technology of video under low illumination[J]. Infrared and Laser Engineering, 2014, 43(6): 2021-2026.

Citation:

Piao Yan, Liu Lei, Liu Xiaoyu. Enhancement technology of video under low illumination[J]. Infrared and Laser Engineering, 2014, 43(6): 2021-2026.

低照度环境下视频增强技术

1.
长春理工大学电子信息工程学院,吉林长春 130022

基金项目:

吉林省科技厅资助项目（20110355）

详细信息

作者简介:
朴燕（1965-），女，博士，教授，博士生导师，主要从事立体成像及数字视频图像处理方面的研究工作。Email：piaoyan66@126.com

中图分类号: TN911.73

Enhancement technology of video under low illumination

1.
Electronic and Information Engineering Institute,Changchun University of Sciences and Technology,Changchun 130022,China

摘要: 在低照度环境下，摄像机捕捉到的夜间视频质量较差，常出现光照不足、对比度低、模糊不清和颜色偏移等问题，影响了视频的判读和理解。针对夜间视频存在的问题，提出不同时段空间背景融合技术和根据Retinex理论利用三边滤波器提取亮度图像的照度分量并结合Sigmiod 非线性拉伸函数对反射分量进行增强处理以突出细节达到图像增强的目的。经实验证明，提出的算法能够提高低照度夜间视频的整体视觉效果，图像的亮度、对比度、清晰度得到改善，突出了视频图像细节，保留了视频重要内容，增强结果自然清晰，避免了图像失真等问题，解决了夜间视频增强中常出现的光晕、鬼影、颜色偏移等问题，便于视频的判读与分析。
- 图像增强 /
- Retinex理论 /
- 三边滤波 /
- 图像融合
Abstract: The picture quality of the video is very poor under the low illumination night environment, it often appears low contrast, blurred, color offset, etc, and it has influence on interpretation and understanding of the video. For solving the problem of nighttime video, the different time space background fusion technology was proposed based on moving object and a new Retinex image enhancement algorithm. This method improved the whole brightness and the contrast of the video through the strategy of adaptive brightness adjustment. Then the illumination components of brightness images were extracted by the trilateral filter based on the theory of Retinex. The reflecting components of images were obtained through compressing illumination. It was because that the reflecting components of images included large number of particulars and marginal information of images, reflecting components were enhanced through integrating Sigmiod non-linear stretching function. At last, it enhanced the saturation component to get more bright colors. The experiments show that the algorithm can improve the visual effect of the low illumination video at nighttime. The image brightness, contrast, sharpness is improved, and the method not only enhanced the video image detail, but also retained the important content of the video. The method avoid the distortion of images, such as, halo, ghost, color deviation.
- image enhancement /
- Retinex theory /
- trilateral filter /
- image fusion

[1]	Li Min, Zhou Zhenhua, Zhang Guilin. Image measures in the evaluation of ART algorithm performance[J]. Infrared and Laser Engineering, 2007, 36(3): 412-416. (in Chinese) 李敏, 周振华, 张桂林. 自动目标识别算法性能评估中的图像度量[J]. 红外与激光工程, 2007, 36(3): 412-416.
[2]
[3]	Wang Jinsong, Yan Yian, Wei Fajie. Moving object detection method using background Gaussian kernel density estimation[J]. Infrared and Laser Engineering, 2009, 38(2): 373-382. (in Chinese) 王劲松, 颜益安, 魏法杰. 利用背景高斯核密度估计的运动目标检测方法[J]. 红外与激光工程, 2009, 38(2): 373-382.
[4]
[5]	Prasun Choudhury, Jack Tumblin. The trilateral filter for contrast images and meshs[C]//Eurographics Symposium on Rendering, 2003: 1-11.
[6]
[7]	Braun G J, Fairchild M D. Image lightness rescaling using sigmoidal contrast enhancementfunctions[J]. Journal of Electron Imaging, 1999, 8: 380-393.
[8]
[9]
[10]	Fan Xiaoliang, Yang Jinji. The background extraction and update algorithm based on frame difference[J]. Computer Engineering, 2011, 37(22): 159-161. (in Chinese) 樊晓亮, 杨晋吉. 基于帧间差分的背景提取与更新算法[J].计算机工程, 2011, 37(22): 159-161.
[11]
[12]	Ramesh Raskar, Adrian Ilie, Jingyi Yu. Image fusion for context enhancement and video surrealism[C]//Proceedings of SPIE: Image Sensors, 2004, 3965: 392-401.
[13]	Fredo Durand, Julie Dorsey. Fast bilateral filtering for the display of high-dynamic-range images[C]//Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, 2002, 21(3): 249-25.
[14]
[15]	Jing Li, Stan Z Li, Quan Pan, et al. Illumination and motion-based video enhancement for night surveillance[C]//Proceedings 2nd Joint IEEE International Workshop on VSPETS, 2005.

[1]	谭威, 宋闯, 赵佳佳, 梁欣凯. 基于多层级图像分解的图像融合算法 . 红外与激光工程, 2022, 51(8): 20210681-1-20210681-9. doi: 10.3788/IRLA20210681
[2]	庞忠祥, 刘勰, 刘桂华, 龚泿军, 周晗, 罗洪伟. 并行多特征提取网络的红外图像增强方法 . 红外与激光工程, 2022, 51(8): 20210957-1-20210957-9. doi: 10.3788/IRLA20210957
[3]	张方, 肖辉. 基于三角函数变换与IRDPSO优化的图像增强算法 . 红外与激光工程, 2022, 51(8): 20210709-1-20210709-8. doi: 10.3788/IRLA20210709
[4]	汪伟, 许德海, 任明艺. 一种改进的红外图像自适应增强方法 . 红外与激光工程, 2021, 50(11): 20210086-1-20210086-9. doi: 10.3788/IRLA20210086
[5]	曾瀚林, 孟祥勇, 钱惟贤. 高斯差分滤波图像融合方法 . 红外与激光工程, 2020, 49(S1): 20200091-20200091. doi: 10.3788/IRLA20200091
[6]	张智, 孙权森, 林栩凌, 韩明亮. 基于临近时空帧间信息的空间目标图像增强方法 . 红外与激光工程, 2019, 48(S1): 193-197. doi: 10.3788/IRLA201948.S128004
[7]	张家民, 时东锋, 黄见, 王英俭. 图像融合在偏振关联成像中的应用 . 红外与激光工程, 2018, 47(12): 1226002-1226002(7). doi: 10.3788/IRLA201847.1226002
[8]	杨洪飞, 夏晖, 陈忻, 孙胜利, 饶鹏. 图像融合在空间目标三维重建中的应用 . 红外与激光工程, 2018, 47(9): 926002-0926002(8). doi: 10.3788/IRLA201847.0926002
[9]	郭全民, 董亮, 李代娣. 红外与可见光图像融合的汽车抗晕光系统 . 红外与激光工程, 2017, 46(8): 818005-0818005(6). doi: 10.3788/IRLA201746.0818005
[10]	鲍雪晶, 戴仕杰, 郭澄, 吕寿丹, 沈成, 刘正君. 基于插值的共焦显微镜非线性畸变失真图像校正 . 红外与激光工程, 2017, 46(11): 1103006-1103006(7). doi: 10.3788/IRLA201746.1103006
[11]	宋言明, 潘志康, 孟晓辰, 娄小平, 祝连庆. 基于仿人眼自适应调节的多光谱视觉图像处理方法 . 红外与激光工程, 2017, 46(9): 910001-0910001(8). doi: 10.3788/IRLA201746.0910001
[12]	曾祥通, 张玉珍, 孙佳嵩, 喻士领. 颜色对比度增强的红外与可见光图像融合方法 . 红外与激光工程, 2015, 44(4): 1198-1202.
[13]	王金玲, 贺小军, 宋克非. 采用区域互信息的多光谱与全色图像融合算法 . 红外与激光工程, 2014, 43(8): 2757-2764.
[14]	杨桄, 童涛, 孟强强, 孙嘉成. 基于梯度加权的红外与可见光图像融合方法 . 红外与激光工程, 2014, 43(8): 2772-2779.
[15]	张宝辉, 闵超波, 窦亮, 张俊举, 常本康. 目标增强的红外与微光图像融合算法 . 红外与激光工程, 2014, 43(7): 2349-2353.
[16]	刘雪超, 吴志勇, 王弟男, 杨华, 黄德天. 结合自适应窗口的二维直方图图像增强 . 红外与激光工程, 2014, 43(6): 2027-2034.
[17]	张勇, 金伟其. 夜视融合图像质量客观评价方法 . 红外与激光工程, 2013, 42(5): 1360-1365.
[18]	张勇, 金伟其. 夜视融合图像质量主观评价方法 . 红外与激光工程, 2013, 42(2): 528-532.
[19]	徐利民, 范文慧, 刘佳. 太赫兹图像的降噪和增强 . 红外与激光工程, 2013, 42(10): 2865-2870.
[20]	毛海岑, 刘爱东. 利用证据理论的图像融合方法 . 红外与激光工程, 2013, 42(6): 1642-1646.

点击查看大图

计量

文章访问数: 506
HTML全文浏览量: 105
PDF下载量: 285
被引次数: 0

低照度环境下视频增强技术

1. 长春理工大学电子信息工程学院,吉林长春 130022

作者简介:
朴燕（1965-），女，博士，教授，博士生导师，主要从事立体成像及数字视频图像处理方面的研究工作。Email：piaoyan66@126.com

收稿日期: 2013-10-10
修回日期: 2013-11-15
刊出日期: 2014-06-25

基金项目:

吉林省科技厅资助项目（20110355）

中图分类号: TN911.73

关键词:

摘要: 在低照度环境下，摄像机捕捉到的夜间视频质量较差，常出现光照不足、对比度低、模糊不清和颜色偏移等问题，影响了视频的判读和理解。针对夜间视频存在的问题，提出不同时段空间背景融合技术和根据Retinex理论利用三边滤波器提取亮度图像的照度分量并结合Sigmiod 非线性拉伸函数对反射分量进行增强处理以突出细节达到图像增强的目的。经实验证明，提出的算法能够提高低照度夜间视频的整体视觉效果，图像的亮度、对比度、清晰度得到改善，突出了视频图像细节，保留了视频重要内容，增强结果自然清晰，避免了图像失真等问题，解决了夜间视频增强中常出现的光晕、鬼影、颜色偏移等问题，便于视频的判读与分析。

English Abstract

Enhancement technology of video under low illumination

1. Electronic and Information Engineering Institute,Changchun University of Sciences and Technology,Changchun 130022,China

Received Date: 2013-10-10
Rev Recd Date: 2013-11-15
Publish Date: 2014-06-25

Keywords:

Abstract: The picture quality of the video is very poor under the low illumination night environment, it often appears low contrast, blurred, color offset, etc, and it has influence on interpretation and understanding of the video. For solving the problem of nighttime video, the different time space background fusion technology was proposed based on moving object and a new Retinex image enhancement algorithm. This method improved the whole brightness and the contrast of the video through the strategy of adaptive brightness adjustment. Then the illumination components of brightness images were extracted by the trilateral filter based on the theory of Retinex. The reflecting components of images were obtained through compressing illumination. It was because that the reflecting components of images included large number of particulars and marginal information of images, reflecting components were enhanced through integrating Sigmiod non-linear stretching function. At last, it enhanced the saturation component to get more bright colors. The experiments show that the algorithm can improve the visual effect of the low illumination video at nighttime. The image brightness, contrast, sharpness is improved, and the method not only enhanced the video image detail, but also retained the important content of the video. The method avoid the distortion of images, such as, halo, ghost, color deviation.