Automatic low light level image enhancement using Gaussian mixture modeling

CHEN Ying; ZHU Ming; LIU Jian; LI Zhao-ze

doi:10.3788/YJYXS20153002.0300

您当前的位置：

首页 >

文章列表页 >

Automatic low light level image enhancement using Gaussian mixture modeling

Imaging Technology & Image Processing | 更新时间：2020-08-12

- Automatic low light level image enhancement using Gaussian mixture modeling
- Chinese Journal of Liquid Crystals and Displays Vol. 30, Issue 2, Pages: 300-309(2015)
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所,吉林长春,中国,130033
  2. 中国科学院大学北京,510640
  3. 总装备部沈阳军事代表局驻长春地区军事代表室,吉林长春,130033
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20153002.0300
  CLC： TP391.4
- Received：23 April 2014，
  
  Revised：11 June 2014，
  
  Published Online：11 June 2014，
  
  Published：05 April 2015
- 稿件说明：
移动端阅览
陈莹, 朱明, 刘剑, 李兆泽. 高斯混合模型自适应微光图像增强[J]. 液晶与显示, 2015,30(2): 300-309

CHEN Ying, ZHU Ming, LIU Jian, LI Zhao-ze. Automatic low light level image enhancement using Gaussian mixture modeling[J]. , 2015,30(2): 300-309
陈莹, 朱明, 刘剑, 李兆泽. 高斯混合模型自适应微光图像增强[J]. 液晶与显示, 2015,30(2): 300-309 DOI： 10.3788/YJYXS20153002.0300.

CHEN Ying, ZHU Ming, LIU Jian, LI Zhao-ze. Automatic low light level image enhancement using Gaussian mixture modeling[J]. , 2015,30(2): 300-309 DOI： 10.3788/YJYXS20153002.0300.

摘要

为了改善微光情况下可见光图像传感器输出图像的质量

提出了一种基于高斯混合模型的自适应微光图像增强算法。对图像的直方图进行混合高斯建模

应用改进的期望最大化算法对直方图拟合

从而获取高斯混合模型的最优参数

然后根据各个聚类的交点将直方图分区

最后确定输出图像所属聚类的映射关系

同时应用保持最大熵方法逼近人类视觉特性映射函数得到最终的增强图像。实验结果表明

此图像增强模型能自适应确定最佳聚类个数

提高直方图拟合的运算速度

一帧图像平均处理时间为0.37 s

在相关信息熵和纹理信息等的客观评价中

增强结果明显优于传统方法

有效地提高了微光图像的对比度

同时保持了图像的细节。

Abstract

In order to improve the output quality of visible light sensor in low-light environment

an adaptive image enhancement algorithm using Gaussian mixture modeling is proposed in this paper. The histogram of image is modeled with Gaussian mixture modeling and the improved EM algorithm is used to fit the histogram and get the best parameters. Then

the histogram is separated into sub-histograms based on the intersections of Gaussian components. Finally

the mapping is achieved according to the parameters of output image

and the final enhanced image is obtained by the maximum entropy preserving method which tends to the characteristics of human visual. The experimental results show that the algorithm can determine the optimal number of clusters adaptively and improve the speed of the histogram fitting which costs 0.37 s averagely. Comparing with traditional methods

the enhancement result is superior in terms of objective evaluations of related information entropy and texture information. It can improve the contrast of the low light level image and maintain the details.

关键词

Keywords

references

贺柏根,刘剑,马天玮. 基于 DSP + FPGA 的实时图像去雾增强系统设计 [J]. 液晶与显示,2013,28(6): 968-972. He B G, Liu J, Ma T W. Real-time image defogging and enhanced system designed based on DSP+FPGA [J]. Chinese Journal of Liquid Crystals and Displays, 2013,28(6): 968-972. (in Chinese)[2] 史继芳,杨斌,韩占锁,等. 基于双重模型客观评价微光像增强器的分辨力 [J]. 光学精密工程,2013,19(3):2260-2265. Shi J F, Yang B, Han Z S, et al. IR/visible image registration based on EM iteration of log-likelihood function [J]. Optics and Precision Engineering, 2013, 19(3): 2260-2265. (in Chinese)[3] Gonzalez R C, Woods R E. Digital Image Processing [M]. Upper Saddle River, NJ: Prentice Hall, 2006.[4] 尹传历,王啸哲. 机载嵌入式图像增强系统设计与实现 [J]. 液晶与显示,2013,28(4):604-607. Yin C L, Wang X Z. Design and realization of airborne embedded image enhancement system [J]. Chinese Journal of Liquid Crystals and Displays,2013, 28(4): 604-607. (in Chinese)[5] 樊博,王延杰,孙宏海,等.FPGA实现高速实时多端口图像处理系统的研究 [J]. 液晶与显示, 2013,28(4):620-625. Fan B, Wang Y J, Sun H H, et al. High speed real-time multiport image processing system realized on FPGA [J]. Chinese Journal of Liquid Crystals and Displays, 2013, 28(4): 620-625. (in Chinese)[6] Kim T K, Paik J K, Kang B S. Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering [J]. IEEE Transactions on Consumer Electronics, 1998, 44(1): 82-87.[7] Iwanami T, Goto T, Hirano S, et al. An adaptive contrast enhancement using regional dynamic histogram equalization [C]. IEEE International Conference on Consumer Electronics, 2012:719-722.[8] Ooi C H, Isa N A M. Quadrants dynamic histogram equalization for contrast enhancement [J]. IEEE Transactions on Consumer Electronics, 2010, 56(4): 2552-2559.[9] 卢清华,吴志伟,范彦斌. 基于混合高斯模型的运动车辆检测方法 [J]. 光电子·激光,2013,24(4):751-757. Lu Q H, Wu Z W, Fan Y B. An improved mobile vehicle detection method based on Gaussian mixture model [J]. Journal of Optoelectronics · Laser, 2013, 24(4):751-757. (in Chinese)[10] 聂宏宾,侯晴宇,赵明,等. 基于似然函数EM迭代的红外与可见光图像配准 [J]. 光学精密工程,2011,21(9):657-663. Nie H B, Hou J Y, Zhao M, et al. Objective evaluation of resolution for low-light-level image intensifier based on dual-model [J]. Optics and Precision Engineering, 2011, 21(9):657-663. (in Chinese)[11] 穆为磊,高建民,陈富民,等. 符合人眼视觉特性的焊缝射线数字图像增强方法 [J]. 西安交通大学学报,2012,46(3):90-93. Mu W L, GaoJ M, Chen F M, et al. Weld radiographic image enhancement conforming to human visual system [J]. Journal of Xi'an Jiao tong University,2012, 46(3): 90-93. (in Chinese)[12] Chen S D, Ramli A R. Minimum mean brightness error bi-histogram equalization in contrast enhancement [J]. IEEE Transactions on Consumer Electronics, 2003, 49(4): 1310-1319.[13] 宋磊,郑宝忠,张莹,等.一种基于高斯混合模型的改进EM算法研究 [J]. 应用光学,2013,34(6):985-989. Song L, Zheng B Z, Zhang Y, et al. Advanced EM algorithm based on Gaussian mixture model [J]. Journal of Applied Optics, 2013, 34(6): 985-989. (in Chinese)[14] Figueiredo M, Jain A. Unsupervised learning of finite mixture models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(3): 381-396.[15] 韩希珍,赵建.结合偏微分方程增强图像纹理及对比度 [J]. 光学精密工程,2012,18(6):1382-1388. Han X Z, Zhao J. Enhancement of image texture and contrast combined with partial differential equation [J]. Optics and Precision Engineering, 2012, 18(6):1382-1388. (in Chinese)[16] Menotti D, Najman L, Facon J, et al. Multi-histogram equalization methods for contrast enhancement and brightness preserving [J]. IEEE Transactions on Consumer Electronics, 2007, 53(3): 1186-1194.[17] 谢凤英,赵丹培. Visual C++数字图像处理[M]. 北京:电子工业出版社,2008. Xie F Y, Zhao D P. Visual C++ Digital Image Processing [M]. Beijing: Publishing House of Electronics Industry, 2008. (in Chinese)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Underwater image enhancement algorithm based on improved color-line model

Sand-dust image enhancement based on Lab color space

Improved YOLOx-based vehicle detection method for low light environment

Real-time image enhancement based-on improved algorithm of gray-scale equispacing density equalization

Lightweight underwater image enhancement network based on GAN

Related Author

LIANG Xiuman

YAO Xinzhe

LIU Zhendong

YU Haifeng

NIU Hongxia

ZHANG Hongzhu

YANG Xiaohan

WANG Jun

Related Institution

College of Electrical Engineering， North China University of Science and Technology

Key Lab of Opt-Electronic Technology and Intelligent Control of Ministry of Education， Lanzhou Jiaotong University

Key Laboratory of Plateau Traffic Information Engineering and Control of Gansu Province， Lanzhou Jiaotong University

School of Automation and Electrical Engineering， Lanzhou Jiaotong University

China Northwest Architecture Design and Research Institute Co. Ltd.

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰