Computational Technology Resources - CCC

A.A. Shah, G.F. Mirza, G.H. Palli, T. Hussain, B.S. Chowdhry and M.Z. Shaikh

NCRA-CMS Laboratory, Mehran University of Engineering & Technology, Jamshoro, Sindh, Pakistan

doi:10.4203/ccc.1.10.28

A.A. Shah, G.F. Mirza, G.H. Palli, T. Hussain, B.S. Chowdhry, M.Z. Shaikh, "Development of a Rail Flaw Measuring Stick Using Binary Image Classifier", in J. Pombo, (Editor), "Proceedings of the Fifth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 1, Paper 10.28, 2022, doi:10.4203/ccc.1.10.28

Keywords: railway track surface defects, binary classifier, canny edge detector, image histogram, Tensorflow, Numpy, Keras.

Abstract

The safety of railway system in most of the developing countries like Pakistan is compromised by railway track surface defects like squat and turn out frogs. The railway system plays a significant role in shaping up a country’s economy due to its increasing demand of passengers and cargo. This paper describes development of an instrumentation that is an inspiration from Spherry’s walking stick and uses binary classifier for the swift analyzation of a railway track surface-based faults. The algorithm is trained using 500 images of healthy and faulty railway tracks captured at an operational railway junction. The entire process is performed in real time using Raspberry Pi 3 B + and APIs like OpenCV, Tensorflow, Numpy and Keras. The measured accuracy of the algorithm recorded is 93.7% and is validated using visual inspection techniques.

download the full-text of this paper (PDF, 12 pages, 813 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 1 PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 10.28 Development of a Rail Flaw Measuring Stick Using Binary Image Classifier A.A. Shah, G.F. Mirza, G.H. Palli, T. Hussain, B.S. Chowdhry and M.Z. Shaikh NCRA-CMS Laboratory, Mehran University of Engineering & Technology, Jamshoro, Sindh, Pakistan doi:10.4203/ccc.1.10.28 Full Bibliographic Reference for this paper A.A. Shah, G.F. Mirza, G.H. Palli, T. Hussain, B.S. Chowdhry, M.Z. Shaikh, "Development of a Rail Flaw Measuring Stick Using Binary Image Classifier", in J. Pombo, (Editor), "Proceedings of the Fifth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 1, Paper 10.28, 2022, doi:10.4203/ccc.1.10.28 Keywords: railway track surface defects, binary classifier, canny edge detector, image histogram, Tensorflow, Numpy, Keras. Abstract The safety of railway system in most of the developing countries like Pakistan is compromised by railway track surface defects like squat and turn out frogs. The railway system plays a significant role in shaping up a country’s economy due to its increasing demand of passengers and cargo. This paper describes development of an instrumentation that is an inspiration from Spherry’s walking stick and uses binary classifier for the swift analyzation of a railway track surface-based faults. The algorithm is trained using 500 images of healthy and faulty railway tracks captured at an operational railway junction. The entire process is performed in real time using Raspberry Pi 3 B + and APIs like OpenCV, Tensorflow, Numpy and Keras. The measured accuracy of the algorithm recorded is 93.7% and is validated using visual inspection techniques. download the full-text of this paper (PDF, 12 pages, 813 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions