Learning Based Experimental Approach For Condition Monitoring Using Laser Cameras In Railway Tracks

Detecting the rail surface faults is one of the most important components of railway inspection process which should be performed periodically. Today, the railway inspection process is commonly performed using computer vision. Performing railway inspection based on image processing can lead to false-positive results. The fact that the oil and dust residues occurring on railway surfaces can be detected as an error by the image processing software can lead to loss of time and additional costs in the railway maintenance process. In this study, a hardware and software architecture are presented to perform railway surface inspection using 3D laser cameras. The use of 3D laser cameras in railway inspection process provides high accuracy rates in real time. The reading rate of laser cameras to read up to 25.000 profiles per second is another important advantage provided in real time railway inspection. Consequently, a computer vision-based approach in which 3D laser cameras that could allow for contactless and fast detection of the railway surface and lateral defects such as fracture, scouring and wear with high accuracy are used in the railway inspection process was proposed in the study.

[1]  P. Dubath,et al.  Random forest automated supervised classification of Hipparcos periodic variable stars , 2011, 1101.2406.

[2]  Ke Xu.  3D Detection Technique of Surface Defects for Steel Rails Based on Linear Lasers , 2010 .

[3]  Reinhold Huber-Mörk,et al.  Statistical Rail Surface Classification Based on 2D and 21/2D Image Analysis , 2010, ACIVS.

[4]  Guangjun Zhang,et al.  A novel calibration approach to structured light 3D vision inspection , 2002 .

[5]  Cui Du-wu,et al.  The method of intelligent inspection of product quality based on computer vision , 2006, 2006 7th International Conference on Computer-Aided Industrial Design and Conceptual Design.

[6]  Mehmet Karaköse.  Sensor Based Intelligent Systems for Detection and Diagnosis , 2016, J. Sensors.

[7]  Mehmet Karaköse,et al.  Type-2 fuzzy activation function for multilayer feedforward neural networks , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[8]  Mehmet Karakose,et al.  Reinforcement Learning Based Artificial Immune Classifier , 2013, TheScientificWorldJournal.

[9]  Mehmet Karaköse,et al.  IMU based adaptive blur removal approach using image processing for railway inspection , 2016, 2016 International Conference on Systems, Signals and Image Processing (IWSSIP).

[10]  S. L. Grassie,et al.  Rail defects: an overview , 2003 .

[11]  Steven V. Sawadisavi,et al.  DEVELOPMENT OF A MACHINE VISION SYSTEM FOR INSPECTION OF RAILWAY TRACK COMPONENTS , 2010 .

[12]  Martin Lauer,et al.  Track detection in 3D laser scanning data of railway infrastructure , 2015, 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings.

[13]  Zhangdui Zhong,et al.  Rail Inspection Meets Big Data: Methods and Trends , 2015, 2015 18th International Conference on Network-Based Information Systems.

[14]  Mehmet Karakose,et al.  A new computer vision approach for active pantograph control , 2013, 2013 IEEE INISTA.

[15]  Saulius Juodkazis,et al.  3D laser microfabrication: principles and applications , 2006 .

[16]  Mehmet Karaköse,et al.  Random forest based diagnosis approach for rail fault inspection in railways , 2016, 2016 National Conference on Electrical, Electronics and Biomedical Engineering (ELECO).

[17]  Liming Li,et al.  Railway track gauge inspection method based on computer vision , 2012, 2012 IEEE International Conference on Mechatronics and Automation.