融合PHOG和MSLBP特征的铁路扣件检测算法

doi:10.3969/j.issn.0258-2724.2015.02.008

基金项目:

国家自然科学基金资助项目(51275431)

四川省科技支撑计划资助项目(2012GZ0102,2014GZ0005)

详细信息

作者简介:
刘甲甲(1983-),男,博士研究生,研究方向为计算机视觉、模式识别,E-mail:liujia9437@126.com

通讯作者:
李柏林(1962-),男,博士,教授,研究方向为计算机图形图像处理,E-mail:blli62@263.net

计量
- 文章访问数:1030
- HTML全文浏览量:115
- PDF下载量:484
- 被引次数:0
出版历程
- 收稿日期:2014-06-03
- 刊出日期:2015-04-25

Railway Fastener Detection Algorithm Integrating PHOG and MSLBP Features

摘要

摘要:为了提高铁路扣件检测的识别率和鲁棒性,以及扣件图像PHOG特征的有效性,提出了简单有效的枕肩定位算法,该算法首先在提取PHOG特征前,根据枕肩、扣件和背景间的位置关系去除冗余背景信息;然后,模拟人眼视觉注意机制,设计MSLBP特征采样方式,提取扣件图像的宏观纹理特征;最后,采用分层次加权融合的方法联立两类特征,并采用SVM分类器进行扣件分类识别,提出一种基于计算机视觉和PHOG-MSLBP融合特征的缺陷识别算法.将该算法应用于实验,结果表明:与使用PHOG、MSLBP单一特征相比,基于PHOG-MSLBP融合特征检测算法的平均识别率分别提高了6.3%、4.5%,且鲁棒性更强,可满足扣件缺陷自动化检测的需要.
- 扣件/
- 形状特征/
- 宏观纹理特征/
- 特征融合/
- 分类检测
Abstract:In order to improve the recognition rate and robustness of railway fasteners detection, and to increase the effectiveness of PHOG (pyramid histogram of oriented gradients) feature, a simple and effective sleeper shoulder locating algorithm was proposed. In this algorithm, the redundant information in fastener images was removed before extraction of PHOG feature, according to the positional relationships among the sleeper shoulder, fasteners, and background. Then, an MSLBP (macroscopic local binary pattern) sampling method was designed and applied to extract the macroscopic texture feature of the fastener images, which could well simulate human visual attention mechanism. Finally, the two different categories of features were integrated by the hierarchical weighted fusion method;using the SVM classifier to classify and detect fastener defects, a defect recognition algorithm based on computer vision and PHOG-MSLBP fusion feature was presented. The algorithm was applied to experiments, and the results show that the average recognition rate based on PHOG-MSLBP feature is 6.3% higher than that based on PHOG feature, and 4.5% higher than that based on MSLBP feature. In addition, the proposed algorithm is more robust than several mainstream methods, and can meet the need of automatic inspection of fastener defects.
- fastener/
- shape feature/
- macroscopic texture feature/
- feature fusion/
- classification detection

HTML全文

参考文献 (43)

SINGH M, SINGH S, JAISWAL J, et al. Autonomous rail track inspection using vision based system

MARINO F, DISTANTE A, MAZZEO P, et al. A real-time visual inspection system for railway maintenance: automatic hexagonal-headed bolts detection

[C]//IEEE International Conference on Computational Intelligence for Homeland Security and Personal Safety. Alexandria: IEEE, 2006: 56-59.

SIRIL Y, MARK D, NARENDRAK G. Condition monitoring of wooden railway sleepers

[J]. IEEE Systems, Man, and Cybernetics Society, 2007, 37(3), 418-428.

许贵阳,史天运,任盛伟,等. 基于计算机视觉的车载轨道巡检系统研制

肖新标,金学松,温泽峰. 钢轨扣件失效对列车动态脱轨的影响

YANG Jinfeng, WEI Tao, LIU Manhua, et al. An efficient direction field-based method for the detection of fasteners on high-speed railways

[J]. Trans-portation Research Part C: Emerging Technologies, 2009, 17(1): 38-55.

XIA Yiqi, XIE Fengying, JIANG Zhiguo. Broken railway fastener detection based on adaboost algorithm

LI Y, OTTO C, HAAS N, et al. Component-based track inspection using machine vision technology

[J]. 中国铁道科学,2013,34(1): 139-144. XU Guiyang, SHI Tianyun, REN Shengwei, et al. Development of the on-board track inspection system based on computervision

[J]. China Railway Science, 2013, 34(1): 139-144.

LI Qingyong, REN Shengwei. A real time visual inspection system for discrete surface defects of rail heads

SUN Hao, WANG Cheng, WANG Boliang, et al. Pyramid binary pattern features for real-time pedestrian detection from infrared videos

[J]. 交通运输工程学报,2006,6(1): 10-15. XIAO Xinbiao, JIN Xuesong, WEN Zefeng. Influence of rail fastener failure on vehicle dynamic derail-ment

陈维荣,冯倩,张健,等. 受电弓滑板状态监测的图像目标提取

[J]. Journal of Traffic and Transportation Engineering, 2006, 6(1): 10-15.

VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features

AHONEN T, HADID A, PIETIKAINEN M. Face description with local binary patterns: application to face recognition

[J]. Sensors, 2011, 1(8): 7364-7381.

LIAO Shengcai, ZHAO Guoying, KELLOKUMPU V, et al. Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes

LEI Zhen, LIAO Shengcai, PIETIKINEN M, et al. Face recognition by exploring information jointly in space, scale and orientation

[C]//International Conference on Opto-electronics and Image Processing. Beijing: IEEE, 2010: 313-316.

ZHAO Guoying, AHONEN T, MATAS J, et al. Rotation-invariant image and video description with local binary pattern features

ZHANG Lun, CHU Rufeng, XIANG Shiming, et al. Face detection based on multi-block LBP representation

[C]//Proceedings of the 1st ACM International Conference on Multimedia Retrieval. New York: ACM, 2011: No. 60.

ALAHI A, ORTIZ R, VANDERGHEYNST P. FREAK: fast retina keypoint

HEIKKILM, PIETIKINEN M, SCHMID C. Description of interest regions with local binary patterns

SU Yu, SHAN Shiguang, CHEN Xilin, et al. Hierarchical ensemble of global and local classifiers for face recognition

[J]. IEEE Transactions on Instrumentation and Measurement, 2012, 61(8): 2189-2199.

[J]. Neurocomputing, 2011, 74(5): 797-804.

[J]. 江南娱乐网页版入口官网下载安装学报,2010,45(1): 59-64. CHEN Weirong, FENG Qian, ZHANG Jian, et al. Image object detection in monitoring of pantograph slippers

[J]. Journal of Southwest Jiaotong University, 2010, 45(1): 59-64.

[C]//IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2001: 1511-1518.

[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12): 2037-2041.

[C]//IEEE Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010: 1301-1306.

[J]. IEEE Transactions on Image Processing, 2011, 20(1): 247-256.

[J]. IEEE Transactions on Image Processing, 2012, 21(4): 1465-1477.

[J]. Advances in Biometrics Lecture Notes in Computer Science, 2007, 4642: 11-18.

[C]//IEEE Conference on Computer Vision and Pattern Recognition. Providence: IEEE, 2012: 510-517.

[J]. Pattern Recognition, 2009, 42(3): 425-436.

[J]. IEEE Transactions on Image Processing, 2009, 18(8): 1885-1896.

施引文献

附加材料 (0)

访问统计

点击查看大图

计量

文章访问数:1030
HTML全文浏览量:115
PDF下载量:484
被引次数:0