Russian Federation
Russian Federation
Russian Federation
Russian Federation
Russian Federation
Russian Federation
Objective: the article considers an approach to the development of a system for monitoring the vigilance and actions of the driver using technical vision and neural network models. The main purpose of the research is to improve the safety of railway transport. Methods: data collection from various sources, annotation, data purification and normalization, neural network training based on video recordings of drivers’ faces in various states and data on their behavior. Neural network learning algorithms based on the architecture of convolutional neural networks, teaching methods with a teacher, mask segmentation methods and proportional resizing of the area of interest, mask segmentation methods for determining the contour of an object in an image, deep learning algorithms such as stochastic gradient descent and error back propagation. Results: a system has been developed that determines the emotional state of the driver based on a real-time video stream, detecting signs of fatigue or distraction, warning of possible dangerous situations. This approach will allow you to quickly respond to the risks that arise in the process of train control, which allows you to increase the level of train safety. Practical significance: a system for monitoring the vigilance and actions of the driver has been developed and can be implemented on locomotives or motor-car rolling stock for real monitoring and prevention of emergency situations.
system, driver, machine learning, safety, railway transportation, data analysis, neural network, accidents, warnings
1. Scherbina N. V. Regulyaciya funkcional'nogo sostoyaniya mashinistov lokomotivnyh brigad s primeneniem BOS-treninga: faktornyy analiz eksperimental'nyh dannyh // Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioelektroniki. 2021. T. 19, № 4. S. 28–36.
2. Orlova N. V. Analiz faktorov riska i profilaktika narusheniy ritma serdca u mashinistov lokomotivov zheleznodorozhnogo transporta // Materialy XI Vserossiyskoy nauchno-prakticheskoy konferencii s mezhdunarodnym uchastiem. Analiz riska zdorov'yu — 2021. Vneshnesredovye, social'nye, medicinskie i povedencheskie aspekty. 2021. S. 132.
3. Rukovodstvo po upravleniyu bezopasnost'yu poletov DOC 9859, izd. 4 // ICAO, Kanada, 2018. 218 s.
4. Komplekt oborudovaniya sistemy kontrolya deesposobnosti vahtennogo pomoschnika kapitana SKDVP: rukovodstvo po ekspluatacii NNPM.468214.001RE // MRS Elektroniks, Nizhniy Novgorod, 2017. 36 s.
5. Bonch-Bruevich V. V., Dementienko V. V., Kremez A. S. i dr. Distancionnyy kontrol' bodrstvovaniya voditelya v reyse // Avtomatizaciya v promyshlennosti. 2015. № 2.
6. Samofalov I. V., Nefed'ev A. I. Intellektual'naya sistema kontrolya psihoemocional'nogo sostoyaniya voditelya avtotransportnogo sredstva // Energo- i resursosberezhenie: promyshlennost' i transport. 2020. № 2.
7. Pospelov P. I., Tatashev A. G., Trofimenko Yu. V. i dr. Podhod k issledovaniyu faktorov riska soversheniya narusheniy, svyazannyh s ispol'zovaniem smartfonov vo vremya vozhdeniya // T-Comm. 2021. № 12 [Elektronnyy resurs]. URL: https://cyberleninka.ru/article/n/ podhod-k-issledovaniyu-faktorov- riska-soversheniya- narusheniy-svyazannyh- s-ispolzovaniem-smartfonov-vo-vremya-vozhdeniya
8. Myaktov I. V., Shalev V. S. Usovershenstvovannaya sistema proverki bodrstvovaniya mashinista // Molodezhnaya nauka. 2022. S. 241–244.
9. Nerodenko A. A. Bezopasnosti dvizheniya poezdov, osnaschennyh priborami KLUB-U // Problemy i osnovnye napravleniya razvitiya vysshego tehnicheskogo obrazovaniya. 2022. S. 43–47.
10. Kravchuk D. A. Ul'trazvukovaya sistema kontrolya psihofiziologicheskogo sostoyaniya mashinista poezda // Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Medicinskoe priborostroenie. 2020. T. 10. № 1. S. 134–142.
11. Hromov S. K., Kulagin M. A., Sidorenko V. G. Avtomatizaciya soprovozhdeniya pol'zovateley avtomatizirovannyh sistem upravleniya na baze mashinnogo obucheniya // Novye informacionnye tehnologii v issledovanii slozhnyh struktur. 2020. S. 74–75.
12. Dai J. Real-time and accurate object detection on edge device with TensorFlow Lite // Journal of physics: conference series. IOP Publishing, 2020. T. 1651, no. 1. P. 012114.
13. Cui Y. Multi-EmoNet: a novel multi-task neural network for driver emotion recognition // IFAC-PapersOnLine. 2020. T. 53, no. 5. P. 650–655.
14. Duth P. S., Poojashree B. S. Human Activity Detection Using Pose Net // International Conference on Futuristic Technologies (INCOFT). IEEE, 2022. P. 1–5.
