[1]赖庆峰,叶俊勇.基于特征点匹配的接触网磨损检测研究[J].机械与电子,2015,(05):3-7,12.
　LAI Qingfeng,YE Junyong.Research of the Catenary Wear Detection Based on Feature Point Matching[J].Machinery & Electronics,2015,(05):3-7,12.
点击复制

基于特征点匹配的接触网磨损检测研究
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2015年05期
页码:
3-7,12
栏目:
设计与研究
出版日期:
2015-05-25

文章信息/Info

Title:
Research of the Catenary Wear Detection Based on Feature Point Matching
文章编号:
1001-2257(2015)05-0003-05
作者:
赖庆峰; 叶俊勇
(重庆大学光电技术及系统教育部重点实验室,重庆 400044)
Author(s):
LAI Qingfeng;  YE Junyong
(Key Laboratory of Optoelectronic Technology and Systems Ministry of Education,Chongqing University,Chongqing 400044,China)
关键词:
线阵立体视觉;  接触网;  FAST;  SURF特征向量
Keywords:
the linear array stereo vision;  catenary;  FAST;  SURF feature vector
分类号:
TP391
文献标志码:
A
摘要:
跨座式单轨交通接触网磨损检测中,传统的人工巡检方式存在效率低下、安全性差等问题。研究了线阵立体视觉在接触网磨损检测中的应用。立体匹配是立体视觉中的重点与难点。在线阵立体匹配过程中。首先,分别提取对应的左右图像的加速分割检测特征点(FAST); 其次,对特征点生成加速鲁棒性特征(SURF)的特征向量; 最后,利用双向快速近似最近邻搜索算法得到初始匹配点集,并使用随机采样一致性确定最终匹配点集。由匹配点集生成稠密、准确的视差图,进而获得接触网的实际残高。实验结果表明,该方法能快速、准确的检测出接触网的磨损情况
Abstract:
There are problems of low efficiency and poor safety for traditional manual inspection way in straddle-type monorail transportation catenary wear detection.We research the application of the linear array stereo vision in the detection of the catenary wear.Stereo matching is the key and difficulty of the stereo vision.Firstly,we extract FAST features from the corresponding stereo image in the process of stereo matching.Secondly,SURF feature vectors is generated for those features,then the vidrectional fast approximate nearest neighbor algorithm and random sample consensus are employed to search the final corresponding points.Finally,we achieve disparity map that is dense and accurate from corresponding points,and then acquire the actual residual high of the catenary.Experiment results show that our method can detect the wear situation of the catenary quickly and accurately.

参考文献/References:

[1] 彭朝勇,高晓蓉.国外接触网磨耗检测系统[J].中国铁路,2007,46(04):66-68.
[2] Kalikin V E,Verkhogliad A G,Kalichkin S V.Automatic opto-lectronic system for inspection of wire wear using high-speed image analysis[C]//Proceeding of the 8th International Conference,2011:201-204.
[3] 占栋,陈唐龙,于龙,等.基于线阵相机的接触轨几何参数动态检测系统[J].现代城市轨道交通,2012,9(01):41-44.
[4] 朱挺.新型国产轨道交通接触网检测系统研究[J].都市轨道交通,2012,25(6):12-16.
[5] 谢风华.跨座式单轨接触网结构设计[J].现代城市轨道交通,2005,4(04):12-14.
[6] Rosten,Drummond T.Machine learning for high-speed corner detection[C]//European Conference on Computer Vision,Graz,Austria,2006:430-443.
[7] Bay H,Ess A,Tuytelarrs T,etal.SURF:Speed up robust features[J].Computer Vision and Image Understanding,2008,110(3):346-359.
[8] Carsten Steger,Markus Ulrich.机器视觉算法与应用[M].北京:清华大学出版社,2008.
[9] Gary Bradski,Adiran Kaebler.学习OpenCV(中文版)[M].于仕琪,刘瑞祯,译.北京:清华大学出版社,2009.
[10] Zhang Z.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334
[11] Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[12] 赵璐璐,耿国华,李康,等.基于SURF和快速近似最近邻搜索的图像匹配算法[J].计算机应用研究,2013,30(3):921-923.
[13] Fischler M A,Bolles R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395.
[14] 林晓帆,林立文,邓涛.基于SURF描述子的遥感影像配准[J].计算机工程,2010,36(12):216-218.

备注/Memo

备注/Memo:
收稿日期:2014-12-08
基金项目:中央高校基本科研基金资助项目(106112013CDJZR-120014)
作者简介:赖庆峰(1987-),男,福建龙岩人,硕士研究生,研究方向为图像处理与模式识别; 叶俊勇(1973-),男,重庆人,副教授,研究生导师,研究方向为计算机视觉、模式识别。
更新日期/Last Update: 2015-05-25