Machine Vision Technology for Locomotives to Identify Railway Colour-Light Signals
https://doi.org/10.30932/1992-3252-2019-17-62-72
Abstract
Improving quality of transport and logistics services in modern conditions is associated with introduction of new technology and improvement of existing technologies of informatization and digitalization of transport. A particular task of introducing digital technologies into the technological processes of railway transport is to increase safety of train traffic.
The analysis of the works of domestic and foreign authors on issues of improving safety of train traffic revealed that at present there is a task of introduction of digital devices for analyzing infrastructure objects along the route of a locomotive. This is of importance when increasing speed of trains or when the trips are long, and it is difficult for a person (a driver) to correctly assess the situation and make a right decision.
The objective of this work is to develop a method for automatic monitoring of railway infrastructure facilities, by equipping the locomotive with machine vision technology, namely, to ensure the ability to visually control the indications of railway colour-light signals along the route. The locomotive is equipped with a video module for fixing the streaming image along its movement, and with the microprocessor equipment for analyzing the resulting image. As an algorithm for recognizing railway signals in a fixed image, a mathematical apparatus based on models of convolutional neural networks is used.
The work performed showed good results in identifying colour-light signals in the analyzed images. Equipping traction rolling stock with technical vision will allow timely identification of track signals, this is especially important on railway tracks where there is no coding in the track circuit, which helps to increase the level of train safety. The development of the presented technology contributes to digitalization of railway transport, which makes it competitive in the world market.
The analysis of the works of domestic and foreign authors on issues of improving safety of train traffic revealed that at present there is a task of introduction of digital devices for analyzing infrastructure objects along the route of a locomotive. This is of importance when increasing speed of trains or when the trips are long, and it is difficult for a person (a driver) to correctly assess the situation and make a right decision.
The objective of this work is to develop a method for automatic monitoring of railway infrastructure facilities, by equipping the locomotive with machine vision technology, namely, to ensure the ability to visually control the indications of railway colour-light signals along the route. The locomotive is equipped with a video module for fixing the streaming image along its movement, and with the microprocessor equipment for analyzing the resulting image. As an algorithm for recognizing railway signals in a fixed image, a mathematical apparatus based on models of convolutional neural networks is used.
The work performed showed good results in identifying colour-light signals in the analyzed images. Equipping traction rolling stock with technical vision will allow timely identification of track signals, this is especially important on railway tracks where there is no coding in the track circuit, which helps to increase the level of train safety. The development of the presented technology contributes to digitalization of railway transport, which makes it competitive in the world market.
About the Authors
V. I. Minakov
Omsk State Transport University (OSTU)
Russian Federation
Russian Federation
Ph.D. (Eng), Associate Professor of the Department of Locomotives
Omsk
V. K. Fomenko
Omsk State Transport University (OSTU)
Russian Federation
Russian Federation
Ph.D. (Eng), Associate Professor of the Department of Locomotives
Omsk
References
1. Posmityukha, A. A. Locomotive safety devices and control over their operation [Lokomotivnie pribory bezopasnosti i control’ za ikh rabotoi]. Moscow, Transport publ., 1992, 61 p.
2. Ivanov, Yu. A. Development of a locomotive system of technical vision: Abstract of Ph.D. (Law) thesis [Razrabotka lokomotivnoi sistemy tekhnicheskogo zreniya: Avtoref. dis… kand. yur. nauk]. Moscow, MGUPS [RUT] publ., 2015, 24 p.
3. Druki, A. A. Application of convolutional neural networks for identification and recognition of car license plates in images with a complex background [Primenenie svertochnykh neironnykh setei dlya vydeleniya i raspoznavaniya avtomobilnykh nomernykh znakov na izobrazheniyakh so slozhnym fonom]. Izvestiya Tomskogo politekhnicheskogo universiteta, 2014, Iss. 5, pp. 85–92.
4. Khaikin, S. Neural networks: full course [Neironnie seti: polniy kurs], 2nd ed. Moscow, «I. D. Williams» LLC, 2006, 1104 p. [Electronic resource]: https://studizba.com/files/show/djvu/1762–1-haykin-s–neyronnye-seti.html. Last accessed 23.11.2019.
5. Chiang, Cheng-Chin;Ho, M.-C.; Liao, H.-S.; Pratama, Andi; Syu, W.-C. Detecting and recognizing traffic lights by genetic approximate ellipse detection and spatial texture layouts. International Journal of Innovative Computing, Information and Control, December 2011, Vol. 7, No. 12, pp. 6919–6934. [Electronic resource]: https://www.researchgate.net/publication/286958803_Detecting_and_recognizing_traffic_lights_by_genetic_approximate_ellipse_detection_and_spatial_texture_layouts. Last accessed 23.11.2019.
6. Cortes, C., Vapnik, V. Support-vector networks. Machine Learning, 1995, Vol. 20, Iss. 3, pp. 273–297. DOI: https://doi.org/10.1023/A:1022627411411. [Electronic resource]: https://link.springer.com/content/pdf/10.1023/A:1022627411411.pdf. Last accessed 23.11.2019.
7. Diao, Yunfeng; Cheng, Wenming; Du, Run; Wang, Yaqing; Zhang, Jun. Vision-based detection of container lock holes using a modified local sliding window method. EURASIP Journal on Image and Video Processing, 2019, Vol. 69. [Electronic resource]: https://link.springer.com/article/10.1186%2Fs13640-019-0472-1. Last accessed 29.12.2019.
8. Julie, A., Pal, S. Keras Library – A Deep Learning Tool [Biblioteka Keras – instrument glubokogo obucheniya]. Moscow, DMK Press, 2018, 294 p.
9. Kecman, V., Melki, G. Fast Online Algorithms for Support Vector Machines Models and Experimental Studies. IEEE South East Conference (SoutheastCon 2016), Virginia, USA, 2016. pp. 26–31. [Electronic
10. resource]: https://www.researchgate.net/publication/303257413_Fast_Online_Algorithms_for_Support_Vector_Machines_Models_and_Experimental_Studies. Last accessed 29.12.2019.
11. Platt, J. C. Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines, Microsoft Research, Technical Report MSR-TR-98-14, 1998. [Electronic resource]: https://www.researchgate.net/publication/2624239_Sequential_Minimal_Optimization_A_Fast_Algorithm_for_Training_Support_Vector_Machines. Last accessed 29.12.2019.
Review
For citations:
Minakov V.I., Fomenko V.K. Machine Vision Technology for Locomotives to Identify Railway Colour-Light Signals. World of Transport and Transportation. 2019;17(6):62-72. https://doi.org/10.30932/1992-3252-2019-17-62-72
Views:
892
Email this article 