Real-time monitoring of brake shoe keys in freight cars

详细信息    查看全文

• 作者：Rong Zou (1) (2)
  Zhen-ying Xu (1)
  Jin-yang Li (3)
  Fu-qiang Zhou (2)
  
  1. School of Mechanical Engineering ; Jiangsu University ; Zhenjiang ; 212013 ; China
  2. MOE Key Laboratory of Precision Opto-Mechatronics Technology ; Beihang University ; Beijing ; 100191 ; China
  3. MOE Key Laboratory of Modern Agricultural Equipment and Technology ; Jiangsu University ; Zhenjiang ; 212013 ; China
  
• 关键词：Condition monitoring ; Feature expression ; Brake shoe key ; Machine vision ; TP277 ; U279.3
• 刊名：Journal of Zhejiang University - Science C
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：16
• 期：3
• 页码：191-204
• 全文大小：1,365 KB
• 参考文献：1. Anderson, GB (2007) Acoustic detection of distressed freight car roller bearings. Proc. ASME/IEEE Joint Rail Conf. and Int. Combustion Engineer Division Spring Technical Conf.. pp. 167-171
  2. Cao, X, Shen, W, Yu, L (2012) Illumination invariant extraction for face recognition using neighboring wavelet coefficients. Patt. Recog. 45: pp. 1299-1305 2011.09.010" target="_blank" title="It opens in new window">CrossRef
  3. Dalal, N, Triggs, B (2005) Histograms of oriented gradients for human detection. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition. pp. 886-893
  4. Ruvo, P, Distante, A, Stella, E (2009) A GPUbased vision system for real time detection of fastening elements in railway inspection. Proc. 16th IEEE Int. Conf. on Image Processing. pp. 2333-2336
  5. Elder, JH, Velisavljevi膰, L (2009) Cue dynamics underlying rapid detection of animals in natural scenes. J. Vis. 9: pp. 7.1-7.20 CrossRef
  6. Gu, W, Xiang, C, Venkatesh, YV (2012) Facial expression recognition using radial encoding of local Gabor features and classifier synthesis. Patt. Recog. 45: pp. 80-91 2011.05.006" target="_blank" title="It opens in new window">CrossRef
  7. Gualdi, G, Prati, A, Cucchiara, R (2012) Multistage particle windows for fast and accurate object detection. IEEE Trans. Patt. Anal. Mach. Intell. 34: pp. 1589-1604 2011.247" target="_blank" title="It opens in new window">CrossRef
  8. Guo, L, Ge, PS, Zhang, MH (2012) Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine. Expert Syst. Appl. 39: pp. 4274-4286 2011.09.106" target="_blank" title="It opens in new window">CrossRef
  9. Hart, JM, Resendiz, E, Freid, B (2008) Machine vision using multi-spectral imaging for undercarriage inspection of railroad equipment. Proc. 8th World Congress on Railway Research. pp. 1-8
  10. Hoiem, D, Efros, AA, Hebert, M (2008) Putting objects in perspective. Int. J. Comput. Vis. 80: pp. 3-15 263-008-0137-5" target="_blank" title="It opens in new window">CrossRef
  11. Kim, H, Kim, W (2011) Automated inspection system for rolling stock brake shoes. IEEE Trans. Instrum. Meas. 60: pp. 2835-2847 2011.2119110" target="_blank" title="It opens in new window">CrossRef
  12. Kumar, MA, Gopal, M (2010) A comparison study on multiple binary-class SVM methods for unilabel text categorization. Patt. Recog. Lett. 31: pp. 1437-1444 2010.02.015" target="_blank" title="It opens in new window">CrossRef
  13. Lampert, CH, Blaschko, MB, Hofmann, T (2009) Efficient subwindow search: a branch and bound framework for object localization. IEEE Trans. Patt. Anal. Mach. Intell. 31: pp. 2129-2142 2009.144" target="_blank" title="It opens in new window">CrossRef
  14. Lazebnik, S, Schmid, C, Ponce, J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition. pp. 2169-2178
  15. Lee, PH, Wu, SW, Hung, YP (2012) Illumination compensation using oriented local histogram equalization and its application to face recognition. IEEE Trans. Image Process. 21: pp. 4280-4289 2012.2202670" target="_blank" title="It opens in new window">CrossRef
  16. Marino, F, Distante, A, Mazzeo, PL (2007) A realtime visual inspection system for railway maintenance: automatic hexagonal-headed bolts detection. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 37: pp. 418-428 2007.893278" target="_blank" title="It opens in new window">CrossRef
  17. M谩rquez, FPG, Roberts, C, Tobias, AM (2010) Railway point mechanisms: condition monitoring and fault detection. Proc. Inst. Mech. Eng. Part F: J. Rail Rapid Transit 224: pp. 35-44 243/09544097JRRT289" target="_blank" title="It opens in new window">CrossRef
  18. Mazzeo, PL, Nitti, M, Stella, E (2004) Visual recognition of fastening bolts for railroad maintenance. Patt. Recog. Lett. 25: pp. 669-677 2004.01.008" target="_blank" title="It opens in new window">CrossRef
  19. Milan茅s, V, Llorca, DF, Villagr谩, J (2012) Visionbased active safety system for automatic stopping. Expert Syst. Appl. 39: pp. 11234-11242 2012.03.047" target="_blank" title="It opens in new window">CrossRef
  20. Mu, Y, Yan, S, Liu, Y (2008) Discriminative local binary patterns for human detection in personal album. Proc. IEEE Conf. on Computer Vision and Pattern Recognition. pp. 1-8
  21. Oukhellou, L, Debiolles, A, Denoeux, T (2010) Fault diagnosis in railway track circuits using Dempster-Shafer classifier fusion. Eng. Appl. Artif. Intell. 23: pp. 117-128 2009.06.005" target="_blank" title="It opens in new window">CrossRef
  22. Quinn, PC, Eimas, PD, Tarr, MJ (2001) Perceptual categorization of cat and dog silhouettes by 3- to 4-month-old infants. J. Exp. Child Psychol. 79: pp. 78-94 2000.2609" target="_blank" title="It opens in new window">CrossRef
  23. Rathod, VR, Anand, RS, Ashok, A (2012) Comparative analysis of NDE techniques with image processing. Nondestruct. Test. Eval. 27: pp. 305-326 2011.645820" target="_blank" title="It opens in new window">CrossRef
  24. Widodo, A, Yang, BS (2007) Support vector machine in machine condition monitoring and fault diagnosis. Mech. Syst. Signal Process. 21: pp. 2560-2574 2006.12.007" target="_blank" title="It opens in new window">CrossRef
  25. Wojek, C, Dork贸, G, Schulz, A (2008) Slidingwindows for rapid object class localization: a parallel technique. Proc. 30th DAGM Symp. on Pattern Recognition. pp. 71-81
  26. Yella, S, Dougherty, M, Gupta, NK (2009) Condition monitoring of wooden railway sleepers. Transpo. Res. Part C Emerg. Technol. 17: pp. 38-55 2008.06.002" target="_blank" title="It opens in new window">CrossRef
  27. Zhang, H, Yang, J, Tao, W (2011) Vision method of inspecting missing fastening components in high-speed ailway. Appl. Opt. 50: pp. 3658-3665 CrossRef
  28. Zhou, FQ, Zou, R, Gao, H (2013) Dust collector localization in trouble of moving freight car detection system. J. Zhejiang Univ.-Sci. C (Comput. & Electron.) 14: pp. 98-106 200223" target="_blank" title="It opens in new window">CrossRef
  29. Zhou, FQ, Zou, R, Qiu, Y (2014) Automated visual inspection of angle cocks during train operation. Proc. Instit. Mech. Eng. Part F J. Rail Rapid Transit 228: pp. 794-806 2" target="_blank" title="It opens in new window">CrossRef
  
• 刊物类别：Computer Science
• 刊物主题：Computer Science, general
  
• 出版者：Zhejiang University Press, co-published with Springer
• ISSN：1869-196X

文摘

Condition monitoring ensures the safety of freight railroad operations. With the development of machine vision technology, visual inspection has become a principal means of condition monitoring. The brake shoe key (BSK) is an important component in the brake system, and its absence will lead to serious accidents. This paper presents a novel method for automated visual inspection of the BSK condition in freight cars. BSK images are first acquired by hardware devices. The subsequent inspection process is divided into three stages: first, the region-of-interest (ROI) is segmented from the source image by an improved spatial pyramid matching scheme based on multi-scale census transform (MSCT). To localize the BSK in the ROI, census transform (CT) on gradient images is developed in the second stage. Then gradient encoding histogram (GEH) features and linear support vector machines (SVMs) are used to generate a BSK localization classifier. In the last stage, a condition classifier is trained by SVM, but the features are extracted from gray images. Finally, the ROI, BSK localization, and condition classifiers are cascaded to realize a completely automated inspection system. Experimental results show that the system achieves a correct inspection rate of 99.2% and a speed of 5 frames/s, which represents a good real-time performance and high recognition accuracy.