南京大学学报(自然科学版) ›› 2019, Vol. 55 ›› Issue (2): 170–179.doi: 10.13232/j.cnki.jnju.2019.02.002

• • 上一篇    下一篇

基于机器视觉的LED大屏亮度一致性检测与矫正

谢 欢1,2,朱 荀1,2,卢 俊3,沈庆宏1*,胡安东4   

  1. 1.南京大学电子科学与工程学院,南京,210023;2.江苏金晓电子信息股份有限公司,南京,210023; 3.南京大学金陵学院,南京,210089;4.湖北交投科技发展有限公司,武汉,430000
  • 接受日期:2018-10-13 出版日期:2019-04-01 发布日期:2019-03-31
  • 通讯作者: 沈庆宏 E-mail:qhshen@nju.edu.cn

LED screens brightness consistency detection and correction based on machine vision

Xie Huan1,2,Zhu Xun1,2,Lu Jun3,Shen Qinghong1*,Hu Andong4   

  1. 1.School of Electronic Science and Engineering,Nanjing University,Nanjing,210023,China; 2.Jiangsu Jinxiao Electronic Information Co.,Ltd.,Nanjing,210023,China; 3.Nanjing University Jinling College,Nanjing,210089,China; 4.Hubei Communications Investment Technology Development Co.,LTD,Wuhan,430000,China
  • Accepted:2018-10-13 Online:2019-04-01 Published:2019-03-31
  • Contact: Shen Qinghong E-mail:qhshen@nju.edu.cn

摘要: LED屏幕在现代交通中应用十分广泛,但是随着使用时间的增加,每个LED灯的亮度会出现不同程度的衰减,从而导致整个LED屏幕整体亮度不一致. 提出一种基于机器视觉技术的屏幕亮度不一致性的检测和矫正方法. 实验中通过对采集的LED图片进行仿射变换、色彩空间转换和形态学滤波、单灯珠定位与亮度提取等操作,可以获得所有LED灯珠的相对位置信息与近似呈现正态分布的亮度信息. 根据人眼对亮度的敏感程度选取出最佳亮度值,将高亮度灯珠抑制到最佳亮度值,实现对LED大屏亮度一致性的矫正. 通过对72×384的LED屏幕测试,不仅能够100%获得所有LED灯珠的亮度信息、位置信息,而且系统的运行速度和稳定性明显优于已有测量方案.

关键词: 机器视觉, 检 测, LED大屏, 亮度一致性矫正

Abstract: LED screens are widely used in modern transportation,but as the usage time increases,the brightness of each LED lamp will be attenuated to varying degrees,resulting in inconsistent brightness of the entire LED screen. This paper proposes a method for detecting and correcting screen brightness inconsistency based on machine vision technology. In the experiment,the relative position information of all LED lamp beads and the brightness information of the approximate normal distribution can be obtained by performing affine transformation,color space conversion and morphological filtering,single lamp bead positioning and brightness extraction on the collected LED images. According to the sensitivity of the human eye to the brightness,the optimal brightness value is selected,and the high-intensity lamp bead is suppressed to the optimal brightness value to achieve the correction of the brightness consistency of the LED large screen. Through the 72×384 LED screen test,not only the brightness information and position information of all LED lamp beads can be obtained 100%,but also the running speed and stability of the system are significantly better than the existing measurement scheme.

Key words: machine vision, inspection, LED large screen, brightness consistency correction

中图分类号: 

  • TP391
[1] 古志良,许毅钦,陈志涛. 三基色白光LED光谱优化及颜色评价体系分析. 照明工程学报,2016,27(1):18-22.(Gu Z L,Xu Y Q,Chen Z T. Spectrum optimization and color quality evaluation of tri-color white light LED. China Illuminating Engineering Journal,2016,27(1):18-22.)
[2] 马 先. LED光源DLP拼接墙色彩显示均匀性和一致性的研究与实现. 硕士学位论文. 广州:华南理工大学,2013.(Ma X. Research and realization of the LED-Based DLP multi-screen display color uniformity and consistency. Master Dissertation. Guangzhou:South China University of Technology,2013.)
[3] 白燕燕. LED显示屏亮度均匀性评价方法的研究. 硕士学位论文. 西安:西安电子科技大学,2013.(Bai Y Y. Research on the evaluation method of Luminance uniformity of LED display. Master Dissertation. Xi’an:Xidian University,2013.)
[4] 桂劲征. 基于HVS的LED显示屏亮度均匀评估方法的研究. 硕士学位论文. 长春:中国科学院研究生院(长春光学精密机械与物理研究所),2012.(Gui J Z. The study of luminance uniformity evaluation for LED display panel based on HVS. Master Dissertation. Changchun:University of Chinese Academy of Sciences(Changchun Institute of Optics,Fine Mechanics and Physics),2012.)
[5] 张 璟,杨艺伟,庄益娈等. LED加速老化测试进展及失效分析. 科技创新与应用,2018(20):69-70.(Zhang J,Yang Y W,Zhuang Y L,et al. Progress and failure analysis of LED accelerated aging test. Technology Innovation and Application,2018(20):69-70.)
[6] 黄小乔,石俊生,邰永航. 用显示器测量人眼视觉的亮度最小可觉差. 液晶与显示,2016,31(2):222-228.(Huang X Q,Shi J S,Tai Y H. Measurement of just noticeable difference for luminance of human visual system on liquid crystal display. Chinese Journal of Liquid Crystals and Displays,2016,31(2):222-228.)
[7] 谢祖通,翁晓伟,陈爱华. 基于成像型亮度计的车灯配光性能检测系统研究. 照明工程学报,2017,28(2):61-64.(Xie Z T,Weng X W,Chen A H. Study on light distribution test based on imaging luminance meter. China Illuminating Engineering Journal,2017,28(2):61-64.)
[8] Jin S. Algorithm research of moving vehicle detection and vehicle flow statistical based on machine vision ∥ Proceedings of 2011 3rd International Conference on Signal Processing Systems. Singapore:IACSIT Press,2012:6.
[9] 罗勇军,牟同升. 基于成像方法LED有效辐亮度测量系统设计. 光子学报,2013,42(12):1496-1500.(Luo Y J,Mou T S. Design of a weighted radiance of the LED measuring system. Journal of Photonics,2013,42(12):1496-1500.)
[10] Xu P,Zhou W J,Fei M R. Detection methods for micro-cracked defects of photovoltaic modules based on machine vision ∥ 2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems. Shenzhen,China:IEEE,2015:609-613.
[11] Gautam G,Mukhopadhyay S. Efficient contrast enhancement based on local-global image statistics and multiscale morphological filtering ∥ Bhattacharyya S,Chaki N,Konar D,et al. Advanced Computational and Comm-unication Paradigms. Springer Berlin Heidel-berg,2018.
  [12] 黄建强. 基于OpenCV的步态识别系统. 硕士学位论文. 合肥:安徽大学,2011.(Huang J Q. OpenCV based on gait recognition system. Master Dissertation. Hefei:Anhui Univer-sity,2011.)
  [13] 苏 卓,喻春阳. 基于2D图像变换的虚拟试衣算法. 计算机技术与发展,2018,28(2):24-26.(Su Z,Yu C Y. A virtual fitting algorithm based on 2D image transformation. Computer Technology and Development,2018,28(2):24-26.)
[14] 曾接贤,邢小军. 小波变换三阈值多尺度融合边缘检测算法. 计算机工程与应用,2012,48(6):177-180,189.(Zeng J X,Xing X J. Improved wavelet-based 3 thresholds and multi-scale integration edge detection algorithm. Computer Engineering and Applications,2012,48(6):177-180,189.)
[15] 雷 涛,沈 瑜,王小鹏. 基于形态学滤波的图像伪边缘去除方法. 兰州交通大学学报,2008,27(3):104-106.(Lei T,Shen Y,Wang X P. A method of removing fake edge based on morphological filtering. Journal of Lanzhou Jiaotong University,2008,27(3):104-106.)
[16] 冀进朝,赵晓威,何 飞等. 基于模糊质心的混合属性数据模糊加权聚类算法. 计算机科学,2018,45(2):109-113.(Ji J C,Zhao X W,He F,et al. Fuzzy weighted clustering algorithm with fuzzy centroid for mixed data. Computer Science,2018,45(2):109-113.)
[17] 李玲玲. 基于CCD相机的LED显示屏亮度校正方法设计. 硕士学位论文. 石家庄:河北科技大学,2011.(Li L L. The design of correction method of the led display brightness based on CCD camera. Master Dissertation. Shijiazhuang:Hebei University of Science and Technology,2011.)
 
[1] 朱伟,张帅,辛晓燕,李文飞,王骏,张建,王炜. 结合区域检测和注意力机制的胸片自动定位与识别[J]. 南京大学学报(自然科学版), 2020, 56(4): 591-600.
[2] 李昭阳,龚安民,伏云发. 基于EEG脑网络下肢动作视觉想象识别研究[J]. 南京大学学报(自然科学版), 2020, 56(4): 570-580.
[3] 郑建兴,李沁文,王素格,李德玉. 基于翻译模型的异质重边信息网络链路预测研究[J]. 南京大学学报(自然科学版), 2020, 56(4): 541-548.
[4] 黄雨婷,徐媛媛,张恒汝,闵帆. 融合标签结构依赖性的标签分布学习[J]. 南京大学学报(自然科学版), 2020, 56(4): 524-532.
[5] 任睿,张超,庞继芳. 有限理性下多粒度q⁃RO模糊粗糙集的最优粒度选择及其在并购对象选择中的应用[J]. 南京大学学报(自然科学版), 2020, 56(4): 452-460.
[6] 陈俊芬,赵佳成,韩洁,翟俊海. 基于深度特征表示的Softmax聚类算法[J]. 南京大学学报(自然科学版), 2020, 56(4): 533-540.
[7] 王宝丽,姚一豫. 信息表中约简补集对及其一般定义[J]. 南京大学学报(自然科学版), 2020, 56(4): 461-468.
[8] 陈石,张兴敢. 基于小波包能量熵和随机森林的级联H桥多电平逆变器故障诊断[J]. 南京大学学报(自然科学版), 2020, 56(2): 284-289.
[9] 周昊,沈庆宏. 基于改进音形码的中文敏感词检测算法[J]. 南京大学学报(自然科学版), 2020, 56(2): 270-277.
[10] 罗春春,郝晓燕. 基于双重注意力模型的微博情感倾向性分析[J]. 南京大学学报(自然科学版), 2020, 56(2): 236-243.
[11] 王露,王士同. 改进模糊聚类在医疗卫生数据的Takagi⁃Sugeno模糊模型[J]. 南京大学学报(自然科学版), 2020, 56(2): 186-196.
[12] 陈睿, 伏云发. 基于EEG握力变化及想象单次识别研究[J]. 南京大学学报(自然科学版), 2020, 56(2): 159-166.
[13] 杨红鑫,杨绪兵,张福全,业巧林. 半监督平面聚类算法设计[J]. 南京大学学报(自然科学版), 2020, 56(1): 9-18.
[14] 刘胜久,李天瑞,珠杰,刘佳. 带权图的多重分形研究[J]. 南京大学学报(自然科学版), 2020, 56(1): 85-97.
[15] 张银芳,于洪,王国胤,谢永芳. 一种用于数据流自适应分类的主动学习方法[J]. 南京大学学报(自然科学版), 2020, 56(1): 67-73.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 杜彦男,吴孔友,刘寅,林红梅,党思思,李彦颖,徐进军. 断陷盆地边界断裂结构特征及物性差异定量评价——以车镇凹陷埕南断裂为例[J]. 南京大学学报(自然科学版), 2020, 56(3): 405 -417 .
[2] 梅志伟,王维东. 基于FPGA的卷积神经网络加速模块设计[J]. 南京大学学报(自然科学版), 2020, 56(4): 581 -590 .