TY  - JOUR
TT  - A Vision Based Condition Monitoring Approach for Rail Switch and Level Crossing using Hierarchical SVM in Railways
AU  - Taştimur, Canan
AU  - Karaköse, Mehmet
AU  - Akın, Erhan
PY  - 2016
DA  - December
DO  - 10.18100/ijamec.270634
JF  - International Journal of Applied Mathematics Electronics and Computers
PB  - PLUSBASE AKADEMİ ORGANİZASYON VE DANIŞMANLIK
WT  - DergiPark
SN  - 2147-8228
SP  - 319
EP  - 325
IS  - Special Issue-1
KW  - Railroad switch detection
KW  - Level crossing detection
KW  - Hough transform
KW  - Image processing filters
KW  - SVM classifier
KW  - Edge detection algorithm
N2  - Rail track, turnoutand level crossing are critical parts of railway components. So faults of railsurface are directly related to the operation safety. The defects occurring inswitches can lead to accidents and the derailment of the train. Therefore, it isnecessary to utilize advanced technology to monitor rail damage of the switchand level crossing zones. In this study, the switch and level crossingdetection are performed with vision based contactless image processingtechniques. Edge detection algorithm, image processing filters, morphologicalfeature extraction, Hough transform and hierarchical SVM classifier areutilized to detect turnout and level crossing regions in the railwayimages. While switch points aredetected, images of the area in front of the train are continuously taken fromcamera placed on the train. These images contain foreign objects such asbuildings, trees, etc. The foreign objects existing in the railway image makeit difficult to detect accurately the rail track. The turnout and levelcrossing detection cannot also be performed using the information of the rail trackthat cannot be correctly detected. Theseveral processes, such as some image processing filters and morphologicalfeature extraction, have been performed to solve this problem. With destroyingthe foreign objects from the railway images, both the accuracy rate of theproposed method has been increased and real-time implementation of the methodis provided. The Hough transform isutilized to detect rail track, switch and level crossing in the proposedmethod. The turnout detection is performed by applying SVM classifier torailway image. The proposed method provides real-time rail track, levelcrossing and turnout detection. Furthermore, this method has gained dynamicfeature due to not be utilized any template image for switch detection. Whenevaluated from these aspects, both the proposed method is superior to othermethods in literature and results were obtained in a shorter time thanks toapplying ROI Segmentation to the railway image.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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
CR  - [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.
CR  - [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.
CR  - [19]	Zwanenburg W.J., Modelling degradation processes of switches & crossings for maintenance & renewal planning on the Swiss railway network, 2009.
CR  - [20]	Hassankiadeh S. Jalili, Failure analysis of railway switches and crossings for the purpose of preventive maintenance, 2011.
CR  - [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.
CR  - [22]	Railway Technical Web Pages, (2016, January), “Infrastructure”. [Online]. Available: http://www.railway-technical.com/track.shtml
CR  - [23]	Arrive Alive, (2016), “Road Safety and Rail Crossings/ Level Crossings”. [Online]. Available: https://arrivealive.co.za/Road-Safety-and-Rail-Crossings-Level-Crossings
CR  - [24]	Level Crossing Installations, (2016), “Level Crossing Installations”. [Online]. Available: http://www.levelcrossinginstallations.co.uk/level-crossing-installations/
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
CR  - [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.
UR  - https://doi.org/10.18100/ijamec.270634
L1  - https://dergipark.org.tr/en/download/article-file/237225
ER  -