基于多帧杆号字符识别的接触网检测系统
|
摘要
针对传统电气化铁路接触网检测在稳定性和准确性方面的不足,提出了以自动识别的杆号作为接触网杆定位和图像索引检测依据的接触网自动检测系统。该系统介绍了多帧图像杆号识别过程,比较了形状上下文(Shape context,SC)算法、角点典型形状上下文特征(Corner representative shape context,CRSC)算法和重心形状上下文(Center shape context,CSC)算法,确定了将CSC算法作为杆号识别的算法。实验结果表明,该算法具有实时性好、可靠性高等优点,能够满足时速300km左右的接触网实时检测要求,为电气化铁路定位检测提供了一种稳定性好、检测速度快的方法。
As insufficient stability and accuracy of traditional electrified railway catenary detection,a catenary automatic detection system is proposed,which has the ability to automatically identified rod numbers as the basis for catenary pole position and image index detection.Firstly,the system introduces the process of multi-frame rod number identification,and then analyzes three most common feature extraction methods,i.e.shape context(SC),corner representative shape context(CRSC)and center shape context(CSC).Finally,the CSC algorithm is chosen to be integrated into the proposed system as the most effective method of rod number recognition.Experiments show that the proposed system achieves better recognition results in terms of real-time performance and reliability than other method.Specifically,the proposed system can run smoothly at about three hundred kilometers per hour and provide a practical method to detect the position of electrified railways.
As insufficient stability and accuracy of traditional electrified railway catenary detection,a catenary automatic detection system is proposed,which has the ability to automatically identified rod numbers as the basis for catenary pole position and image index detection.Firstly,the system introduces the process of multi-frame rod number identification,and then analyzes three most common feature extraction methods,i.e.shape context(SC),corner representative shape context(CRSC)and center shape context(CSC).Finally,the CSC algorithm is chosen to be integrated into the proposed system as the most effective method of rod number recognition.Experiments show that the proposed system achieves better recognition results in terms of real-time performance and reliability than other method.Specifically,the proposed system can run smoothly at about three hundred kilometers per hour and provide a practical method to detect the position of electrified railways.
引文
[1]张韬.基于图像处理的接触网检测系统研究与改进[J].铁道机车车辆,2008,28(6):68-71.Zhang Tao.Study and improvement on the OCS inspection system based on image processing[J].Railway Locomotive&Car,2008,28(6):68-71.
[2]Kusumi S,Nezu K,Nagasawa H.Overhead contact line inspection system by rail-and-road car[J].Quarterly Report of RTRI,2000,41(4):169-172.
[3]Nakama F,Ichikawa M,Nagasawa H.Measurement of contact loss by detecting spark[J].Quarterly Report of RTRI,1984,25(3):95-98.
[4]Landi A,Menconi L,Sani L,Hough transform and thermo-vision for monitoring pantograph catenary system[J].Proceedings of the Institution of Mechanical Engineers,Part F:Journal of Rail&Papid Transit,2006,220(4):435-447.
[5]Hulin B S.Concepts for day-night stereo obstacle detection in the pantograph gauge[C]∥International Conference on Industrial Informatics.[S.l.]:IEEE,2007:449-454.
[6]江杰.接触网风偏量检测系统设计与实现[D].长沙:中南大学,2009.Jiang Jie.Research and improvement catenary detection system based on image processing[D].Changsha:Central South University,2009.
[7]Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[C]∥Proc of the Intl Conf on Computer Vision and Pattern Recognition.Kauai:[s.n.],2001:511-518.
[8]Cho S B.Pattern recognition with neural networks combined by genetic algorithm[J].Fuzzy Sets and Systems,1999,103:339-347.
[9]汪友生,胡百乐.基于支持向量机的动脉硬化斑块识别[J].数据采集与处理,2012,27(3):283-286.Wang Yousheng,Hu Baile.Recognition of a therosclerotic plaque based on support vector machine[J].Journal of Data Acquisition and Processing,2012,27(3):283-286.
[10]吴海滨,周后伟,张铁译,等.基于OTSU的动态结合全局阈值的图像分割[J].大气与环境光学学报,2012,7(6):463-468.Wu Haibin,Zhou Houwei,Zhang Tieyi,et al.Segmentation image using dynamic combined global threshold based on OTSU[J].Journal of Atmospheric and Environmental Optics,2012,7(6):463-468.
[11]Gonzalez R C,Woods R E.数字图像处理[M].北京:电子工业出版社,2007.Gonzalez R C,Woods R E.Digital image processing[M].Beijing:Publishing House of Electronics Industry,2007.
[12]Stef A L.Bulgarelli A.A simple and efficient connected components labeling algorithm[C]∥Proc of IEEE Conference on Image Analysis and Processing.[S.l.]:IEEE,1999:322-327.
[13]Hedberg H,Kristensen F,Owall V.Implementation of labeling algorithm based on contour tracing with feature extraction[C]∥Proc of IEEE International Symposium on Circuits and Systems.New Orleans,LA:IEEE,2007:1101-1104.
[14]卢蓉,范勇.一种提取目标图像最小外接矩形的快速算法[J].计算机工程,2010,36(21):178-180.Lu Rong,Fan Yong,Fast algorithm for extracting minimum enclosing rectangle of target image[J].Computer Engineering,2010,36(21):178-180.
[15]刘光惠.求解简单多边形和平面点集凸包的新算法[J].计算机科学,2007,34(12):222-226.Liu Guanghui.New algorithms for computing the convex hulls of a simple polygon and a planar point set[J].Computer Science,2007,34(12):222-226.
[16]McCallum D,Avis D.A linear algorithm for finding the convex hull of a simple polygon[J].Inf Process Lett,1979,9(5):201-206.
[17]安玮,李宏.模式识别中的透射变换与仿射变换[J].系统工程与电子技术,1999,21(1):55-59.An Wei,Li Hong.Projective transformation and affine transformation in pattern recognition[J].Systems Engineering and Electronics,1999,21(1):55-59.
[18]王静娇,孙晶.基于TMS320DM642的人民币图像特征识别系统[J].数据采集与处理,2012,27(S2):206-211.Wang Jingjiao,Sun Jing.RMB image feature identification system based on TMS320DM642[J].Journal of Data Acquisition and Processing,2012,27(S2):206-211.
[19]Belongie S,Malik J,Puzicha J.Shape matching and object recognition using shape contexts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):509-522.
[20]郑丹晨,韩敏.基于改进典型形状上下文特征的形状识别方法[J].计算机辅助设计与图形学学报,2013,25(2):215-220.Zheng Danchen,Han Min.Improved shape recognition method based on representative shape context[J].Journal of Computer-Aided Design&Computer Graphics,2013,25(2):215-220.
[2]Kusumi S,Nezu K,Nagasawa H.Overhead contact line inspection system by rail-and-road car[J].Quarterly Report of RTRI,2000,41(4):169-172.
[3]Nakama F,Ichikawa M,Nagasawa H.Measurement of contact loss by detecting spark[J].Quarterly Report of RTRI,1984,25(3):95-98.
[4]Landi A,Menconi L,Sani L,Hough transform and thermo-vision for monitoring pantograph catenary system[J].Proceedings of the Institution of Mechanical Engineers,Part F:Journal of Rail&Papid Transit,2006,220(4):435-447.
[5]Hulin B S.Concepts for day-night stereo obstacle detection in the pantograph gauge[C]∥International Conference on Industrial Informatics.[S.l.]:IEEE,2007:449-454.
[6]江杰.接触网风偏量检测系统设计与实现[D].长沙:中南大学,2009.Jiang Jie.Research and improvement catenary detection system based on image processing[D].Changsha:Central South University,2009.
[7]Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[C]∥Proc of the Intl Conf on Computer Vision and Pattern Recognition.Kauai:[s.n.],2001:511-518.
[8]Cho S B.Pattern recognition with neural networks combined by genetic algorithm[J].Fuzzy Sets and Systems,1999,103:339-347.
[9]汪友生,胡百乐.基于支持向量机的动脉硬化斑块识别[J].数据采集与处理,2012,27(3):283-286.Wang Yousheng,Hu Baile.Recognition of a therosclerotic plaque based on support vector machine[J].Journal of Data Acquisition and Processing,2012,27(3):283-286.
[10]吴海滨,周后伟,张铁译,等.基于OTSU的动态结合全局阈值的图像分割[J].大气与环境光学学报,2012,7(6):463-468.Wu Haibin,Zhou Houwei,Zhang Tieyi,et al.Segmentation image using dynamic combined global threshold based on OTSU[J].Journal of Atmospheric and Environmental Optics,2012,7(6):463-468.
[11]Gonzalez R C,Woods R E.数字图像处理[M].北京:电子工业出版社,2007.Gonzalez R C,Woods R E.Digital image processing[M].Beijing:Publishing House of Electronics Industry,2007.
[12]Stef A L.Bulgarelli A.A simple and efficient connected components labeling algorithm[C]∥Proc of IEEE Conference on Image Analysis and Processing.[S.l.]:IEEE,1999:322-327.
[13]Hedberg H,Kristensen F,Owall V.Implementation of labeling algorithm based on contour tracing with feature extraction[C]∥Proc of IEEE International Symposium on Circuits and Systems.New Orleans,LA:IEEE,2007:1101-1104.
[14]卢蓉,范勇.一种提取目标图像最小外接矩形的快速算法[J].计算机工程,2010,36(21):178-180.Lu Rong,Fan Yong,Fast algorithm for extracting minimum enclosing rectangle of target image[J].Computer Engineering,2010,36(21):178-180.
[15]刘光惠.求解简单多边形和平面点集凸包的新算法[J].计算机科学,2007,34(12):222-226.Liu Guanghui.New algorithms for computing the convex hulls of a simple polygon and a planar point set[J].Computer Science,2007,34(12):222-226.
[16]McCallum D,Avis D.A linear algorithm for finding the convex hull of a simple polygon[J].Inf Process Lett,1979,9(5):201-206.
[17]安玮,李宏.模式识别中的透射变换与仿射变换[J].系统工程与电子技术,1999,21(1):55-59.An Wei,Li Hong.Projective transformation and affine transformation in pattern recognition[J].Systems Engineering and Electronics,1999,21(1):55-59.
[18]王静娇,孙晶.基于TMS320DM642的人民币图像特征识别系统[J].数据采集与处理,2012,27(S2):206-211.Wang Jingjiao,Sun Jing.RMB image feature identification system based on TMS320DM642[J].Journal of Data Acquisition and Processing,2012,27(S2):206-211.
[19]Belongie S,Malik J,Puzicha J.Shape matching and object recognition using shape contexts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):509-522.
[20]郑丹晨,韩敏.基于改进典型形状上下文特征的形状识别方法[J].计算机辅助设计与图形学学报,2013,25(2):215-220.Zheng Danchen,Han Min.Improved shape recognition method based on representative shape context[J].Journal of Computer-Aided Design&Computer Graphics,2013,25(2):215-220.