Fast detection study of foreign object intrusion on railway track

• Autorzy: Niu H. , Hou T.

Identyfikatory

DOI

10.5604/01.3001.0012.6510

• Języki publikacji: EN

Abstrakty

EN

The foreign objects intrusion on railway track has seriously affected the safe operation of the train, and it is extremely urgent to monitor them in real time. In order to improve the detection accuracy and rapidity of foreign objects intrusion on railway track, the new detection method of foreign object intrusion on railway track based on multi-background modeling, multi-difference and proportion method of black and white pixels is put forward in this paper. The multi-background modeling method that includes the historical background modeling, the multi-frame average background modeling and the previous frame of current frame background modeling method is used to model background modeling, and the three backgrounds are updated respectively to achieve background updating. The improved Canny method and Hough transform method is used to extract track edge, and get the final track edge image. Based on track edge image, the railway track dangerous area was established through the image segmentation method to reduce the amount of information in image processing and improve the processing speed. And then, according to the structure method of multi-background modeling, the detection method that fuses the historical background difference, average background difference and interframe difference is used to detect foreign object intrusion on track, and the detection result was processed by the morphological open processing. Finally, for the foreign objects intrusion, the decision is done by the quantitative proportion method of black and white pixels of image. The experimental results show that this method has better noise immunity performance and environmental adaptability, and the accuracy and rapidity of foreign objects intrusion detection is improved effectively.

Słowa kluczowe

EN

railway track; foreign object detection; multi-background modeling; multiple difference

PL

tor kolejowy; wykrywanie obcych obiektów; modelowanie wielopoziomowe

• Wydawca: Warsaw University of Technology, Faculty of Transport
• Czasopismo: Archives of Transport
• Rocznik: 2018
• Tom: Vol. 47, iss. 3
• Strony: 79--89
• Opis fizyczny: Bibliogr. 38 poz., fot., rys.

Twórcy

autor

Niu H.

• Automatic Control Institute, Lanzhou Jiaotong University, Lanzhou, China

autor

Hou T.

• School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, China

Bibliografia

• [1] HOU, T., & LI, D.D., 2017. Recognition of Foreign Object Intrusion for Railway Track on Double Background Modeling and Difference Image. Journal of Lanzhou Jiaotong University, 36(1), pp. 39-42.
• [2] HU, Q.W., CHEN, Z.Y.,&WU, S., 2012. Fast and Automatic Railway Building Structure Clearance Detection Technique Based on Mo-bile Binocular Stereo Vision. JOURNAL OF THE CHINA RAILWAY SOCIETY, 34(1), pp. 65-71.
• [3] WANG, Q.X., LI, X.F., LIU, Y.L., et al, 2014. Visual Detection Method for the Invasion of Slowly Changing Foreign Matters to Railway Lines. CHINA RAILWAY SCIENCE, 35(3), pp. 137-143.
• [4] YAO, H.L., LIU, J.C., & WANG, T., 2015. In-formation security design and research for High-Speed Railway Nature Disaster and Foreign Invasion Monitor System. RAILWAY COMPUTER APPLICATION, 24(2), pp. 28-32.
• [5] ZHANG, B., 2015. Study on Unsafe Actions of Human Accidents during Railway Train Operation. RAILWAY TRANSPORT AND ECONOMY, 37(3), pp. 74-78.
• [6] KARDAS-CINAL, E., 2014. Selected problems in railway vehicle dynamics related to running safety. Archives of Transport, 31(3), pp.36-45.
• [7] BURDZIK, R., NOWAK, B., & ROZMUS, J., 2017. Safety in the railway industry. Archives of Transport, 44(4), pp.15-24
• [8] WIECZOREK, S., PAŁKA, K., & GRABOWSKA-BUJNA, B., 2018. A model of strategic safety management in railway transport based on Jastrzebska Railway Company Ltd. Scientific Journal of Silesian University of Technology. Series Transport, 98, pp. 201-210.
• [9] CHENG, W., 2010. The Design of High-speed Railway Foreign Invasion Monitoring System. Wuhan: Wuhan University of Technology.
• [10] MOCKEL, S., SCHERER, F., & SCHUSTER, P.F., 2003.Multi-sensor obstacle detection on railway tracks, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings, Columbus, OH, USA, pp. 42-46.
• [11] NARAYANAN, A.H., BRENNAN, P., BEN-JAMIN,R., et al, 2011. Railway Level Crossing Obstruction Detection Using MIMO Radar. 8th European Radar Conference held as part of the European Microwave Week, Proceedings, London, United Kingdom, pp.57-60.
• [12] ALVAREZ, F.J., URENA, J., MAZO, M., HERNANDEZ, A., GARCIA, J. J., & DONATO, P., 2004, Ultrasonic sensor system for detecting falling objects on railways, IEEE Intelligent Vehicles Symposium, Parma, Italy, pp. 866-871.
• [13] GARCIA, J. J., URENA, J., HERNANDEZ, A., MAZO, M., JIMÉNEZ, J. A., ÁLVAREZ, F. J., ... & GARCIA, E. 2010. Efficient multisensory barrier for obstacle detection on railways. IEEE Transactions on Intelligent Transportation Systems, 11(3), 702-713.
• [14] SEHCHAN, O., SUNGHYUK, P., CHANGMU, L., 2007. A platform surveillance monitoring system using image processing for passenger safety in railway station. International Conference on Control, Automation and Systems, Seoul, pp. 394-398.
• [15] LI, D.D., 2016. Intelligent Recognition Study of Foreign Object Intrusion on Railway Track. Lanzhou: lanzhou Jiaotong University.
• [16] GUO, B.Q., ZHU,L.Q.,&SHI,H.M., 2012. Intrusion detection algorithm for railway clearance with rapid DBSCAN clustering. Chinese Journal of Scientific Instrument, 33(2), pp. 241-247.
• [17] SHI, H.M., CHAI, H., & WANG, Y., 2015. Study on Railway Embedded Detection Algorithm for Railway Intrusion Based on Object Recognition and Tracking. JOURNAL OF THE CHINA RAILWAY SOCIETY, 37(7), pp. 58-65.
• [18] WEI, W., 2014. Research on Method of Intrusion Detection Based on Stereo Vision System. Beijing: Beijing Jiaotong University.
• [19] GIRSHICK, R., DONAHUE , J., DARRELL, T., & MALIK, J. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation Tech report, arXiv: 1311.2524v5 [cs.CV].
• [20] GIRSHICK, R.,2015. Fast R-CNN, IEEE International Conference on Computer Vision. Santiago, pp. 1440-1448.
• [21] REN, S.Q., HE, K.M., & GIRSHICK, R., 2017. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), pp.1137-1149.
• [22] REDMON, J., DIVVALA, S., GIRSHICK, R., & FARHADI, A., 2016. You Only Look Once: Unified, Real-Time Object Detection, IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 779-788.
• [23] LIU, W., ANGUELOV, D., & ERHAN, D., 2016. SSD: Single Shot MultiBox Detector. arXiv:1512. 02325v5[cs.CV].
• [24] FU, C.Y., & LIU, W., 2017. DSSD: Deconvolutional Single Shot Detector, Computer Vision and Pattern Recognition, arXiv:1701. 06659v1 [cs.CV].
• [25] DROZDZAL, M., VORONTSOV, E., CHARTRAND, G., et al, 2016. The importance of skip connections in biomedical image segmentation. International Workshop on Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. Springer International Publishing.
• [26] RONNEBERGER, O., FISCHER, P., & BROX, T., 2015. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer. pp, 234-241.
• [27] CHEN, L. C., BARRON, J. T., PAPAN-DREOU, G., MURPHY, K., & YUILLE, A. L, 2016. Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp. 4545-4554.
• [28] LIU, Z.W., LI, X.X.,&LUO, P.,2015. Semantic Image Segmentation via Deep Parsing Network. Semantic Image Segmentation via Deep Parsing Network, IEEE International Conference on Computer Vision. Santiago, pp.1377-1385.
• [29] CHANDRA, S., & KOKKINOS, I., 2016. Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs. ECCV-Image Processing & Computer Vision[P-3B-14]. Paris: INRIA.
• [30] YUAN, X., HAO, X., CHEN, H., et al, 2013. Background Modeling Method Based on 3D Shape Reconstruction Technology. TELKOMNIKA-Indonesian Journal of Electrical Engineering, 11(4), pp. 2079-2083.
• [31] PENG, H., HAN, L.S., WANG, H., et al, 2013. Background extraction method based on the fusion of wavelet transform and multi-frame average. JOURNAL OF ZHEJIANG UNIVERSITY OF TECHNOLOGY, 41(2), pp. 228-231.
• [32] XIE, W.H., YI, B.S., & XIAO, J.S., 2013. Cascaded algorithm for background modeling using pixel-based and block-based methods. Journal on communications, 34(4), pp.194-200.
• [33] YANG,D., ZHAO, H.B., & LONG, Z., 2013. MATLAB image processing examples explanation. Beijing: Tsinghua University Press.
• [34] RUAN, Q.Q., 2007. Digital Image Processing. Beijing: Publishing House of Electronics Industry.
• [35] LI, R., & WU, X.C., 2014. Automatic Identify of Linear Tracks Based on Digital Image Processing, Video Engineering, 38(3), pp.167-169.
• [36] LI, D.D., HOU, T., & WEI, S.P., 2015. Image edge detection method based on the improved Canny algorithm for rail. Video Engineering, 39(8), pp. 55-58.
• [37] WANG, J.W., & LI, Y.J., 2006. MATLAB 7.0 graph and image processing. Beijing: National Defence Industry Press(in China).
• [38] ZHENG, J., & LI, J.Y., 2014. Moving target detection based on background difference and information entropy. LASER & INFRARED, 44(5), pp. 563-566.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).