|本期目录/Table of Contents|

 视频中运动电车电线的实时自动检测跟踪算法(PDF)

《纳米技术与精密工程》[ISSN:1672-6030/CN:12-1351/O3]

期数:
2017年3期
页码:
205-211
栏目:
精密测量
出版日期:
2017-05-15

文章信息/Info

Title:
  Real-Time Automatic Detection and Tracking for Moving
Trolleybus Power Line Based on Video Sequence
文章编号:
1672-6030(2017)03-0205-07
作者:
 刘见昕1# 蒲灿1# 柴晓飞2 孔昭松2 汪毅1 陈晓冬1 郁道银1
 (1. 天津大学精密仪器与光电子工程学院, 天津300072;
2.天津市松正电动汽车股份有限公司, 天津300308)
Author(s):
 Liu Jianxin1#Pu Can1#Chai Xiaofei2Kong Zhaosong2Wang Yi1Chen Xiaodong1Yu Daoyin1
 (1. School of Precision Instrument and OptoElectronics Engineering, Tianjin University, Tianjin 300072, China;
2.Tianjin Santroll Electric Automobile Technology Co.Ltd., Tianjin 300308,China)
关键词:
  电线检测Otsu算法滤波模版概率霍夫变换(PHT)聚类算法
Keywords:
 power line detectionOtsu algorithmfiltering templateprobabilistic Hough transform (PHT)clustering algorithm
分类号:
TP319.4
DOI:
10.13494/j.npe.20150121
文献标识码:
A
摘要:
针对无轨电车集电杆与电线脱落后无法自动连接的缺点,本文提出一种应用于无轨电车集电杆自动连接系统的电线检测跟踪算法.算法包括图像预处理、直线提取、电线聚类滤波3部分.首先提出一种快速滤波模版,结合Otsu算法得到滤波模版的分割阈值,提取电线二值图像.然后应用概率霍夫变换(PHT)获取直线信息集合.最后在霍夫空间下,使用系统聚类算法对直线集合进行聚类分组,结合电线特征获取正确电线位置信息.为了验证本文算法,对视频图像(25帧/s)进行测试,实验结果表明,该算法在复杂背景干扰下,能够高速、准确地提取电线位置.
Abstract:
 The poles of trolleybuses will fall off from the power lines when the trolleybuses overtake or change the lane. Regarding this problem, a detection and tracking algorithm for power line positions is proposed in automatic connection system of trolleybus’s poles. This algorithm involves three stages:image preprocessing, line extraction, and power line clustering and filtering . Firstly,the fast filtering template is proposed,and combined with Otsu algorithm,segmentation threshold of the template is obtained to extract binary image of power line. Secondly, the probabilistic Hough transform (PHT) is applied to obtain the line set. Finally, in the Hough space, system clustering algorithm is used to cluster and filter the former line set to obtain the final line set , from which the correct power line positions are acquired according to characteristics of power lines.To verify the algorithm proposed , the video sequence (25 frame/s) is tested with the algorithm. Experimental results show that the algorithm proposed can extract power line positions fast and accurately under complex background interference.

参考文献/References

-

备注/Memo

备注/Memo:
收稿日期: 2016-01-15.
作者简介: 刘见昕(1992— ),男,硕士研究生; 蒲灿(1991— ),男,本科,canpu999@163.com.#并列第一作者.
通讯作者: 陈晓东,教授,xdchen@tju.edu.cn.
更新日期/Last Update: 2017-07-11