ИНТЕЛЛЕКТУАЛЬНАЯ СИСТЕМА ТЕХНИЧЕСКОГО ЗРЕНИЯ ДЛЯ ОБНАРУЖЕНИЯ ПРЕПЯТСТВИЙ И ПРЕДСКАЗАНИЯ ПОВЕДЕНИЯ ДВИЖУЩИХСЯ ОБЪЕКТОВ НА ЖЕЛЕЗНОДОРОЖНЫХ ПУТЯХ

Abstract

Currently, the improvement of the quality of transport and logistics services provided is directlyrelated to the introduction of new and modernization of existing technologies ofinformatization and digitalization. One of the most urgent tasks solved by the introduction of digitaltechnologies into existing technological processes is to improve the safety of train traffic.The analysis of domestic and foreign works devoted to the development of train safety improvementsystems has shown that one of the methods of solving the task is the development and implementationof vision systems for detecting infrastructure objects and obstacles in the course of trainmovement. This is especially true when train speeds increase when it is difficult for the driver tocorrectly assess the current situation and make an operational decision. This paper describes theimplementation of a vision system for unmanned trains. Within its framework, a new approach tothe training of a highly specialized mask neural network was implemented. The main task of thissystem is to recognize obstacles and human figures against the background of the railway infrastructuredetermine their location relative to the tracks and assess this situation from the point ofview of traffic safety. To obtain a higher-quality mask, the approach of simultaneous use of imagesof standard CVS cameras and cameras with the higher resolution was used. This method is able toimprove the quality of recognition, especially at large distances, when the object of interest is notnoticeable in the complex environment surrounding it. The work performed has shown good resultsin identifying objects on railway tracks. The creation of a prototype of such a system andequipping it with traction rolling stock will allow for the timely detection of obstacles and peopleon the train path, which contributes to improving the level of train safety.