[1]张国福,王 呈.基于改进概率霍夫直线检测的电梯门状态检测方法[J].南京理工大学学报(自然科学版),2020,44(02):162-170.[doi:10.14177/j.cnki.32-1397n.2020.44.02.006]
 Zhang Guofu,Wang Cheng.Elevator door state detection method based on improved probability Hough line detection[J].Journal of Nanjing University of Science and Technology,2020,44(02):162-170.[doi:10.14177/j.cnki.32-1397n.2020.44.02.006]
点击复制

基于改进概率霍夫直线检测的电梯门状态检测方法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
44卷
期数:
2020年02期
页码:
162-170
栏目:
出版日期:
2020-04-30

文章信息/Info

Title:
Elevator door state detection method based on improved probability Hough line detection
文章编号:
1005-9830(2020)02-0162-09
作者:
张国福王 呈
江南大学 物联网工程学院,江苏 无锡 214122
Author(s):
Zhang GuofuWang Cheng
Internet of Things Engineering Institute,Jiangnan University,Wuxi 214122,China
关键词:
电梯门状态检测 直线检测 霍夫变换 图像处理
Keywords:
elevator door state detection line detection Hough transform image processing
分类号:
TP391.4
DOI:
10.14177/j.cnki.32-1397n.2020.44.02.006
摘要:
针对电梯物联网改造外加传感器施工困难、成本较高等问题,该文提出了一种基于前置图像处理的电梯门状态直线检测方法。针对轿厢外背景及门板工艺对直线检测算法的干扰提出基于规则决策的解决方案。通过提取视频流电梯门图像进行预处理,使用改进概率霍夫直线检测算法提取特征直线,结合基于先验知识的判断规则,实现对电梯门开、关及故障状态的实时检测。通过多个门开关场景验证了算法的有效性,实验结果分析表明,该文提出的限角概率霍夫直线检测算法提取特征直线比概率霍夫直线检测算法耗时减少10%,查准率和查全率均优于概率霍夫直线检测算法,能适用于边缘侧电梯门状态检测系统。
Abstract:
For the problem of installing external sensors difficultly in the car and high cost,an elevator door state line detection method based on pre-image processing is proposed here,and a corresponding solution to the interference of door background and door panel texture on line detection algorithm is presented. Firstly,it is preprocessed to extract elevator door image from video stream; Secondly,the elevator door feature lines are extracted by the improved probability Hough line detection algorithm; Finally,the real-time detection of elevator door opening,closing and fault status is realized by combining judgment rules based on prior knowledge. The effectiveness of the algorithm is verified by selecting multiple door switch pictures. The experimental results prove that,compared with the probability Hough line detection algorithm,the limited-angle probability Hough line detection algorithm proposed in this paper reduces the time consumption by 10% when extracting the characteristic lines,has the higher precision and the recall rate,and is suitable for the front elevator door state detection system.

参考文献/References:

[1] 杨华江. 电梯安全隐患的分析及对策探讨[J]. 科技信息,2009(11):48-49.
Yang Huajiang. Elevator safe hidden danger analysis and countermeasure discussion[J]. Science & Technology Information,2009(11):48-49.
[2]金晓磊,潘鹏. 机器人视觉的电梯轿厢门状态识别系统[J]. 单片机与嵌入式系统应用,2018,18(4):28-31.
Jin Xiaolei,Pan Peng. Recognizing system for state of elevator door based on robot vision[J]. Microcontrollers & Embedded Systems,2018,18(4):28-31.
[3]张书,殷勤. 电梯门锁安全回路改进设计[J]. 电子测试,2014(14):41-43.
Zhang Shu,Yin Qin. The improved design of elevator door lock loop[J]. Electronic Test,2014(14):41-43.
[4]张艳,张重阳,郁生阳. 基于框线检测的票据图像分类方法[J]. 南京理工大学学报,2007,31(4):409-413.
Zhang Yan,Zhang Chongyang,Yu Shengyang. Bill image classification method based on line detection[J]. Journal of Nanjing University of Science and Technology,2007,31(4):409-413.
[5]Yoshihiko M. N-point Hough transform for line detection[J]. Journal of Visual Communication & Image Representation,2009,20(4):242-253.
[6]Rahmdel P,Comley R,Shi D,et al. A review of Hough transform and line segment detection approaches[C]//Proceedings of the 10th International Conference on Computer Vision Theory and Applications. Berlin,Germany:SCITEPRESS,2015:411-418.
[7]Matas J,Kittler J,Galambos C. Robust detection of lines using the progressive probabilistic Hough transform[J]. Computer Vision and Image Understanding,2000,78(1):119-137.
[8]吴欣,张志伟. 基于形态学和霍夫变换的文档图像倾斜检测[J]. 南京理工大学学报,2009,33(2):178-182.
Wu Xin,Zhang Zhiwei. Skew detection of document images using mathematical morphology and Hough transform[J]. Journal of Nanjing University of Science and Technology,2009,33(2):178-182.
[9]蒋斌,李超英,李宗谕,等. 基于决策树分类的毫米波雷达对电力线的检测[J]. 南京理工大学学报,2017,41(1):95-99.
Jiang Bin,Li Chaoying,Li Zongyu,et al. Millimeter wave radar detection in power line based on decision tree classification[J]. Journal of Nanjing University of Science and Technology,2017,41(1):95-99.
[10]王越,范先星,刘金城,等. 结构化道路上应用区域划分的车道线识别[J]. 计算机应用,2015,35(9):2687-2691.
Wang Yue,Fan Xianxing,Liu Jincheng,et al. Lane line recognition using region division on structured roads[J]. Journal of Computer Applications,2015,35(9):2687-2691.
[11]Li Yadi,Chen Liguo,Huang Haibo,et al. Nighttime lane markings recognition based on canny detection and Hough transform[C]//Proceedings of IEEE International Conference on Real-time Computing & Robotics. Angkor Wat,Cambodia:IEEE,2016:411-415.
[12]Rafael G G,Jérémie J,Morel J M,et al. LSD:A line segment detector[J]. Image Processing On Line,2012(2):35-55.
[13]李涛,陈黎,聂晖. 基于改进线段分割检测的电线杆遮挡检测算法[J]. 计算机工程,2017,43(9):250-255.
Li Tao,Chen Li,Nie Hui. Utility pole occlusion detection algorithm based on improved line segmentation detection[J]. Computer Engineering,2017,43(9):250-255.
[14]Liu Hong,Qian Yueliang,Lin Shouxun. Detecting persons using Hough circle transform in surveillance video[C]//Proceedings of the Fifth International Conference on Computer Vision Theory and Applications. Angers,France:SCITEPRESS,2010:267-270.
[15]Ahmed S A. Comparative study among Sobel,Prewitt and Canny edge detection operators used in image processing[J]. Journal of Theoretical and Applied Information Technology,2018,96(18):6517-6525.
[16]Yin Xingyun. Operators to dilate and erode color impulse noise images based on the morphology[C]//2011 International Conference on E-business & E-government. Shanghai,China:IEEE,2011:1-3.
[17]Manzanera A,Nguyen T P,Xu Xiaolei. Line and circle detection using dense one-to-one Hough transforms on greyscale images[J]. EURASIP Journal on Image and Video Processing,2016(1):46-64.

相似文献/References:

[1]张 艳,张重阳,郁生阳,等.基于框线检测的票据图像分类方法[J].南京理工大学学报(自然科学版),2007,(04):409.
 ZHANG Yan,ZHANG Chong-yang,YU Sheng-yang,et al.Bill Image Classification Method Based on Line Detection[J].Journal of Nanjing University of Science and Technology,2007,(02):409.

备注/Memo

备注/Memo:
收稿日期:2019-06-02 修回日期:2019-09-11
作者简介:张国福(1994-),男,硕士生,主要研究方向:嵌入式开发、图像处理、物联网应用集成等,E-mail:zhangguofu3333@163.com; 通讯作者:王呈(1983-),男,副教授,主要研究方向:工业感知与检测技术、基于大数据的建模与分析、图像处理等,E-mail:wangc@jiangnan.edu.cn。
引文格式:张国福,王呈. 基于改进概率霍夫直线检测的电梯门状态检测方法[J]. 南京理工大学学报,2020,44(2):162-170.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2020-04-20