Application of machine learning methods to automate the detection of obstacles to the movement of a train through a level crossing

Autor: Yu.M. Iskanderov, B.E. Katarushkin, A.A. Ershov
Rok vydání: 2020
Předmět:
Zdroj: Informatization and communication. :46-51
ISSN: 2078-8320
DOI: 10.34219/2078-8320-2020-11-2-46-51
Popis: Aim. Currently, when creating intelligent information systems in various fields of practical activity, machine learning methods are used. The article shows the possibilities of using these methods in automating the detection of obstacles in the interest of improving safety and reducing the number of emergencies at level crossings. Materials and methods. The article discusses advanced computer vision technologies used as the basis of an intelligent system for detecting obstacles to the movement of a train through a railway crossing. Results. Based on the analysis of the conditions and features of the functioning of the technologies considered, the relevance of introducing a similar system is shown, options for constructing its structure and operating principle are proposed, approaches are formulated when developing a machine learning model for classifying of the used images. Conclusions. The approach underlying the formation of an intelligent system for detecting obstacles to the movement of a train through a railway crossing allows it to be used as an additional independent security tool that implements an alarm for a duty officer on a specific section of the railway and / or to a traffic control dispatch center to prevent emergencies.
Databáze: OpenAIRE