A Vision Based Condition Monitoring Approach for Rail Switch and Level Crossing using Hierarchical SVM in Railways

Yıl 2016, Special Issue (2016), 319 - 325, 01.12.2016

Canan Taştimur , Mehmet Karaköse , Erhan Akın

https://doi.org/10.18100/ijamec.270634

Cited By: 18

Öz

Rail track, turnout
and level crossing are critical parts of railway components. So faults of rail
surface are directly related to the operation safety. The defects occurring in
switches can lead to accidents and the derailment of the train. Therefore, it is
necessary to utilize advanced technology to monitor rail damage of the switch
and level crossing zones. In this study, the switch and level crossing
detection are performed with vision based contactless image processing
techniques. Edge detection algorithm, image processing filters, morphological
feature extraction, Hough transform and hierarchical SVM classifier are
utilized to detect turnout and level crossing regions in the railway
images.  While switch points are
detected, images of the area in front of the train are continuously taken from
camera placed on the train. These images contain foreign objects such as
buildings, trees, etc. The foreign objects existing in the railway image make
it difficult to detect accurately the rail track. The turnout and level
crossing detection cannot also be performed using the information of the rail track
that cannot be correctly detected.  The
several processes, such as some image processing filters and morphological
feature extraction, have been performed to solve this problem. With destroying
the foreign objects from the railway images, both the accuracy rate of the
proposed method has been increased and real-time implementation of the method
is provided.  The Hough transform is
utilized to detect rail track, switch and level crossing in the proposed
method. The turnout detection is performed by applying SVM classifier to
railway image. The proposed method provides real-time rail track, level
crossing and turnout detection. Furthermore, this method has gained dynamic
feature due to not be utilized any template image for switch detection. When
evaluated from these aspects, both the proposed method is superior to other
methods in literature and results were obtained in a shorter time thanks to
applying ROI Segmentation to the railway image.

Anahtar Kelimeler

Railroad switch detection, Level crossing detection, Hough transform, Image processing filters, SVM classifier, Edge detection algorithm

Kaynakça

• [1] Bahun K. A., Planchet J. L., Birregaha B. and Châtelet E., Railway transportation system's resilience: Integration of operating conditions into topological indicators, In NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium, 2016, pp. 1163-1168.
• [2] Rajabalinejad M., Martinetti A. and Dongen L. A. M. van, Operation, safety and human: Critical factors for the success of railway transportation, In 2016 11th System of Systems Engineering Conference (SoSE), 2016, pp. 1-6.
• [3] Espino J. C., Stanciulescu B. and Forin P., Rail and turnout detection using gradient information and template matching”, In Intelligent Rail Transportation (ICIRT), 2013 IEEE International Conference on, Beijing, 2013, pp. 233-238.
• [4] Santur Y., Karaköse M., Aydın I., and Akın E., IMU based adaptive blur removal approach using image processing for railway inspection, In 2016 International Conference on Systems, Signals and Image Processing (IWSSIP) IEEE, 2016, pp. 1-4.
• [5] Tastimur C., Akın E., Karaköse M., and Aydin I. , Detection of rail faults using morphological feature extraction based image processing, In 2015 23nd Signal Processing and Communications Applications Conference (SIU), 2015, pp. 1244-1247.
• [6] Shen L., Wei X. and Jia L., Surface Defects Detection of Railway Turnouts, In Control Conference (CCC), 2015 34th Chinese, China, 2015, pp. 6285 – 6290.
• [7] Chen Y. and Zhao H., Fault detection and diagnosis for railway switching points using fuzzy neural network, In Industrial Electronics and Applications (ICIEA), 2015 IEEE 10th Conference on, 2015, pp. 860-865.
• [8] Kaleli F. and Akgul Y.S., Vision-Based Railroad Track Extraction Using Dynamic Programming, In 12th International IEEE Conference on Intelligent Transportation Systems, 2009, pp. 1-6.
• [9] Li Q., Shi J. and Li C., Fast line detection method for Railroad Switch Machine Monitoring System, In 2009 International Conference on Image Analysis and Signal Processing, 2009, pp. 61-64.
• [10] Qi Z., Tian Y. and Shi Y., Efficient railway tracks detection and turnouts recognition method using HOG features, In Neural Computing and Applications 23.1, 2013, pp. 245-254.
• [11] Wohlfeil J., Vision based rail track and switch recognition for self-localization of trains in a rail network, In Intelligent Vehicles Symposium (IV), 2011 IEEE. IEEE, 2011, pp. 1025-1030.
• [12] Kaleli F. and Akgul Y.S.,Vision-based railroad track extraction using dynamic programming, In 2009 12th International IEEE Conference on Intelligent Transportation Systems, 2009, pp. 1-6.
• [13] Espino J. C. and Stanciulescu B., Turnout detection and classification using a modified HOG and template matching, In 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013), 2013,pp. 2045-2050.
• [14] Ross R., Vision-based track estimation and turnout detection using recursive estimation, In Intelligent Transportation Systems (ITSC), 2010 13th International IEEE Conference on, 2010, pp. 1330-1335.
• [15] Ying L., Trinh T., Haas N., Otto C., and Pankanti S., Rail Component Detection, Optimization, and Assessment for Automatic Rail Track Inspection, IEEE Transactions on Intelligent Transportation Systems, Vol. 15, 2014, pp. 760 – 770.
• [16] Mainline, (2014, June), “Deliverable 3.3: Rail Switches and Crossings. Development of new technologies for replacement”. [Online]. Available: http://www.mainline-project.eu/IMG/pdf/ml-d3.3-f-methods_for_switches__-crossings_replacement.pdf
• [17] Yaman O., Karakose M., and Akin E., PSO Based Diagnosis Approach for Surface and Components Faults in Railways, In International Journal of Computer Science and Software Engineering (IJCSSE), Volume 5, Issue 5, 2016, pp.89-96.
• [18] Karakose M., Yaman O. and Akin E., Detection of Rail Switch Passages Through Image Processing on Railway Line and Use of Condition-Monitoring Approach, In International Conference on Advanced Technology & Sciences, ICAT’16, 2016, pp. 100-105.
• [19] Zwanenburg W.J., Modelling degradation processes of switches & crossings for maintenance & renewal planning on the Swiss railway network, 2009.
• [20] Hassankiadeh S. Jalili, Failure analysis of railway switches and crossings for the purpose of preventive maintenance, 2011.
• [21] Schupp G., Weidemann C., Mauer L., Modelling the contact between wheel and rail within multibody system simulation, Vehicle System Dynamics, 41(5), 2004, pp. 349-364.
• [22] Railway Technical Web Pages, (2016, January), “Infrastructure”. [Online]. Available: http://www.railway-technical.com/track.shtml
• [23] Arrive Alive, (2016), “Road Safety and Rail Crossings/ Level Crossings”. [Online]. Available: https://arrivealive.co.za/Road-Safety-and-Rail-Crossings-Level-Crossings
• [24] Level Crossing Installations, (2016), “Level Crossing Installations”. [Online]. Available: http://www.levelcrossinginstallations.co.uk/level-crossing-installations/
• [25] Garnica C., Boochs F.. and Twardochlib M., A New Approach To Edge-Preserving Smoothing For Edge Extraction And Image Segmentation, In Proceedings of International Archives of Photogrammetry and Remote Sensing, IAPRS Symposium, 2000.
• [26] Kovacs V., Csorba K., and Tevesz G., Edge Preserving Range Image Smoothing by Rotated Bilateral Sampling, In 2015 4th Eastern European Regional Conference on the Engineering of Computer Based Systems, 2015, pp. 100-105.
• [27] Kher R. and Gandhi R., Adaptive Filtering based Artifact Removal from Electroencephalogram (EEG) Signals, In International Conference on Communication and Signal Processing, 2016, pp. 561-564.
• [28] Chandrasekar L., and Durga G., Implementation of Hough Transform for Image Processing Applications, In International Conference on Communication and Signal Processing, India, 2014, pp. 843-847.
• [29] Tastimur C., Karaköse M., Celik Y., and Akin E., Image Processing Based Traffic Sign Detection and Recognition with Fuzzy Integral, In 2016 International Conference on Systems, Signals and Image Processing (IWSSIP), May 2016, pp. 1-4.
• [30] Tastimur C., Karakose M. and Akin E., A Vision Based Detection Approach for Level Crossing and Switch in Railway, In International Conference on Advanced Technology & Sciences, ICAT’16, 2016, pp. 217-223.
• [31] Dong C., Zhou B. and Hu J., A Hierarchical SVM Based Multiclass Classification by Using Similarity Clustering, In 2015 International Joint Conference on Neural Networks (IJCNN), 2015, pp. 1-6.
• [32] Rebai K., Achour N. and Azouaoui O., Hierarchical SVM classifier for road intersection detection and recognition, In 2013 IEEE Conference on Open Systems (ICOS), 2013, pp. 100-105.
• [33] Liang Y.M., Tyan H.R., Chang S.L., Liao H.Y.M., and Chen S.W., Video stabilization for a camcorder mounted on a moving vehicle, In IEEE Transactions on Vehicular Technology, Vol. 53, 2004, pp. 1636-1648.
• [34] Zhang J., Zhang L., and Xu T., Image Segmentation Using a Hybrid Gradient Based Watershed Transform, In 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC), Shengyang, 2013, pp. 1408-1412.
• [35] Kaur P. and Gupta A., Contour Detection of Gradient Images Using Morphological Operator and Transform Domain Filtering, In Computational Intelligence & Communication Technology (CICT), 2015 IEEE International Conference on, Ghaziabad, 2015, pp. 107-111.
• [36] Amer G. M. H. and Abushaala A. M., Edge detection methods, In Web Applications and Networking (WSWAN), 2015 2nd World Symposium on, 2015, pp. 1-7.
• [37] Chaple G. N., Daruwala R. D., and Gofane M. S., Comparisions of Robert, Prewitt, Sobel operator based edge detection methods for real time uses on FPGA, In Technologies for Sustainable Development (ICTSD), 2015 International Conference on, 2015, pp. 1-4.
• [38] Katkar V., Kulkarni S., and Bhatia D., Traffic Video Classification using edge detection techniques, In 2015 International Conference on Nascent Technologies in the Engineering Field (ICNTE-2015), 2015, pp. 1-6.
• [39] Gajjar N., Patel V., and Shukla A. J., Implementation of edge detection algorithms in real time on FPGA, In 2015 5th Nirma University International Conference on Engineering (NUiCONE), 2015, pp. 1-4.
• [40] Karakose M. and Baygin M., Image processing based analysis of moving shadow effects for reconfiguration in PV arrays, In Energy Conference (ENERGYCON), 2014 IEEE International, 2014, pp. 683-687.