像素级自适应融合的夜间图像增强

王成; 张艳超

doi:10.3788/YJYXS20193409.0888

您当前的位置：

首页 >

文章列表页 >

像素级自适应融合的夜间图像增强

图像处理 | 更新时间：2020-07-05

- 像素级自适应融合的夜间图像增强
- Night image enhancement based on pixel level adaptive image fusion
- 液晶与显示 2019年34卷第9期页码：888-896
- 作者机构：
  
  1.中国人民解放军91245部队, 辽宁葫芦岛 125001
  2.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
- 作者简介：
  
  [ "王成(1983—), 男, 湖北枣阳人, 工程师, 2004年于华中科技大学获得本科学位, 主要从事测控技术方面的研究。E-mail:iailly@163.com" ]
- 基金信息：
  
  吉林省重点科技研发项目(20180201057SF);Key R&D Program of Jilin(20180201057SF)
- DOI：10.3788/YJYXS20193409.0888
  中图分类号： TP394.1;TH691.9
- 收稿日期：2019-03-06，
  
  录用日期：2019-5-18，
  
  纸质出版日期：2019-09-05
- 稿件说明：
移动端阅览
王成, 张艳超. 像素级自适应融合的夜间图像增强[J]. 液晶与显示, 2019,34(9):888-896.

Cheng WANG, Yan-chao ZHANG. Night image enhancement based on pixel level adaptive image fusion[J]. Chinese journal of liquid crystals and displays, 2019, 34(9): 888-896.
王成, 张艳超. 像素级自适应融合的夜间图像增强[J]. 液晶与显示, 2019,34(9):888-896. DOI： 10.3788/YJYXS20193409.0888.

Cheng WANG, Yan-chao ZHANG. Night image enhancement based on pixel level adaptive image fusion[J]. Chinese journal of liquid crystals and displays, 2019, 34(9): 888-896. DOI： 10.3788/YJYXS20193409.0888.

摘要

针对夜间图像整体亮度低、图像细节多集中在较低灰度级范围内的特点，本文提出了一种像素级自适应融合的夜间图像增强方法。首先，通过高通滤波的方式滤除图像的大部分暗背景信息，以整体增强图像各区域灰度细节；然后，将滤波后的图像与原始图像进行像素级自适应加权融合，其中每个像素点对应的两个权值取决于滤波图像内对应像素值与目标模糊集、背景模糊集的接近情况：越接近目标模糊集，滤波图像对应像素权值增大，同时原始图像对应像素权值减小；越接近背景模糊集，则相反，以此来进一步增强图像的全局对比度，增强视觉效果。实验结果表明：增强后的夜间图像在灰度细节和全局对比度方面都得到了显著提高。对于320×256分辨率的灰度图像，在CPU主频为3.0 GHz的硬件环境下，处理时间小于10 ms。采用本文方法处理的夜间退化图像的成像质量得到了明显改善，且其良好的实时性能够更好地满足工程应用需求。

Abstract

Aiming at the characteristics of night images

such as low brightness and most of the image details concentrating in the low gray range

a night image enhancement method based on pixel level adaptive fusion is proposed. Firstly

a high pass filter is used to filter most of the dark background information of the image

so as to enhance the gray details of each region of the image. Then

the filtered image is fused with the original image in the way of pixel level weighting adaptively. The two weights of each pixel

in filtered image and original image respectively

depend on two distances:one is the distance between the pixel value and the target fuzzy set

and the other is the distance between the pixel value and the background fuzzy set. If the pixel value is closer to the target fuzzy set

the weight of the filter image is increased and the weight of the original image is reduced

correspondingly. If the pixel value is closer to the background fuzzy set

the case is the opposite. In this way

the global contrast of the image is further enhanced and the visual effect is improved. Experimental results indicate that the night image enhanced has been improved significantly in both gray detail and global contras. The processing time is less than 10 ms in the hardware environment of CPU with the main frequency of 3.0 GHz for 320×256 resolution gray scale images. The quality of the degraded night image has been improved greatly

and its good real-time performance can meet the needs of the engineering application better.

关键词

Keywords

references

方明, 李洪娜, 雷立宏, 等.低照度视频图像增强算法综述[J].长春理工大学学报:自然科学版, 2016, 39(3):56-64, 69.

FANG M, LI H N, LEI L H, et al .A review on low light video image enhancement algorithms[J]. Journal of Changchun University of Science and Technology ( Natural Science Edition ), 2016, 39(3): 56-64, 69. (in Chinese)

赵宏宇, 肖创柏, 禹晶, 等.马尔科夫随机场模型下的Retinex夜间彩色图像增强[J].光学精密工程, 2014, 22(4):1048-1055.

ZHAO H Y, XIAO C B, YU J, et al .A Retinex algorithm for night color image enhancement by MRF[J]. Optics and Precision Engineering , 2014, 22(4): 1048-1055. (in Chinese)

王浩, 张叶, 沈宏海, 等.图像增强算法综述[J].中国光学, 2017, 10(4):438-448.

WANG H, ZHANG Y, SHEN HH, et al .Review of image enhancement algorithms[J]. Chinese Optics , 2017, 10(4): 438-448. (in Chinese)

BHAT P, ZITNICK C L, COHEN M, et al .GradientShop: a gradient-domain optimization framework for image and video filtering[J]. ACM Transactions on Graphics , 2010, 29(2): 10.

GONZALES A M, GRIGORYAN A M. Fast Retinex for color image enhancement: methods and algorithms[C]// Proceedings of Mobile Devices and Multimedia : Enabling Technologies , Algorithms , and Applications 2015. San Francisco, California: SPIE, 2015: 94110F.

毛东月, 谢正祥, 贺向前, 等.自适应双向保带宽对数变换及低照度图像增强[J].中国图像图形学报, 2017, 22(10):1356-1363.

MAO D Y, XIE Z X, HE X Q, et al .Adaptive bilateral logarithm transformation with bandwidth preserving and low-illumination image enhancement[J]. Journal of Image and Graphics , 2017, 22(10): 1356-1363. (in Chinese)

郝志成, 吴川, 杨航, 等.基于双边纹理滤波的图像细节增强方法[J].中国光学, 2016, 9(4):423-431.

HAO Z C, WU C, YANG H, et al .Image detail enhancement method based on multi-scale bilateral texture filter[J]. Chinese Optics , 2016, 9(4): 423-431. (in Chinese)

余春艳, 徐小丹, 林晖翔, 等.应用雾天退化模型的低照度图像增强[J].中国图象图形学报, 2017, 22(9):1194-1205.

YU C Y, XU X D, LI H X, et al .Low-illumination image enhancement method based on a fog-degraded model[J]. Journal of Image and Graphics , 2017, 22(9): 1194-1205. (in Chinese)

XU H L, KUANG C, ZHANG L, et al .Range limited adaptive brightness preserving multi-threshold histogram equalization algorithm[J]. Chinese Optics , 2017, 10(6): 726-736.

王聪, 杨晶, 潘秀娟, 等.基于光参量放大相位共轭特性的图像修复与增强[J].物理学报, 2017, 66(10):104205.

WANG C, YANG J, PAN X J, et al .Image restoration and enhancement based on phase conjugation of optical parametric amplification[J]. Acta Physica Sinica , 2017, 66(10): 104205. (in Chinese)

张锐, 贾娜.海域图像增强方法综述[J].液晶与显示, 2017, 32(10):828-834.

ZHANG R, JIA N. Sea imageenhancement review[J]. Chinese Journal of Liquid Crystals and Displays , 2017, 32(10): 828-834. (in Chinese)

赵文达, 续志军, 赵建, 等.基于梯度直方图变换增强红外图像的细节[J].光学精密工程, 2014, 22(7):1962-1968.

ZHAO W D, XU Z J, ZHAO J, et al .Enhancement of infrared image details based on gradient histogram transform[J]. Optics and Precision Engineering , 2014, 22(7): 1962-1968. (in Chinese)

李红, 吴炜, 杨晓敏, 等.基于主特征提取的Retinex多谱段图像增强[J].物理学报, 2016, 65(16):160701.

LI H, WU W, YANG X M, et al .Multispectral image enhancement based on Retinex by using structure extraction[J]. Acta Physica Sinica , 2016, 65(16): 160701. (in Chinese)

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, 20(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, 20(6): 1382-1388. (in Chinese)

GONZALEZ R C, WOODS R E.数字图像处理[M].阮秋琦, 阮宇智, 译.3版.北京: 电子工业出版社, 2017.

GONZALEZ R C, WOODS R E. Digital Image Processing [M]. RUAN Q Q, RUAN Y Z, trans. 3rd ed. Beijing: Electronics and Industry Press, 2017. (in Chinese)

林晓春, 李存志.一种基于图像融合的红外图像增强新方法[J].西安电子科技大学学报(自然科学版), 2005, 32(2):189-192, 215.

LIN X C, LI C Z.A new method for infrared image enhancment based on image fusion[J]. Journal of Xidian University , 2005, 32(2): 189-192, 215. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

多干扰成像条件下的钻孔内壁图像鲁棒拼接方法

基于多尺度残差特征融合的图像去雾算法

基于结构纹理分解的红外与可见光图像融合算法

融合红外与可见光的实验室火焰图像分割识别

基于改进FT显著性检测的NSCT红外和可见光图像融合