| Issue |
E3S Web of Conf.
Volume 402, 2023
International Scientific Siberian Transport Forum - TransSiberia 2023
|
|
|---|---|---|
| Article Number | 03021 | |
| Number of page(s) | 10 | |
| Section | Mathematical Modeling, IT, Industrial IoT, AI, and ML | |
| DOI | https://doi.org/10.1051/e3sconf/202340203021 | |
| Published online | 19 July 2023 | |
Development of a software for automatic identification of the rolling stock at marshaling yards using a neural network
1 Rostov State Transport University, 344000 Rostov-on-Don, Russia
2 Rostov Branch of JSC NIIAS, 344000 Rostov-on-Don, Russia
* Corresponding author: nancy-rostov@yandex.ru
The research paper presents the author’s software for automatic identification the rolling stock at marshaling yards using a neural network. Methods for processing images from several cameras, recognizing cuts, creating a fleet model and displaying this model for further display in the Russian Railway information systems have been implemented. The software was developed in the Python 3.6 programming language, using the OpenCV and Torch libraries. Based on the obtained results, a sys-tem for monitoring the track availability of the fleet formation was implemented. A method for neural network training is demonstrated using the example of recognizing cuts of a marshaling yard.
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.