Framework for recognizing information about railway traffic lights

Abstract

This paper deals with the problem of collecting and updating information about railway traffic lights located on the territory of the Russian Federation. To solve this problem, a trained neural network is used that detects railway traffic lights and recognizes the text on the marking plates located on their masts in high-definition images. As a result, the architecture of the information system and its modules were developed, consisting of detection and recognition neural networks, as well as a database for storing and updating information about railway traffic lights. This system should be able to quickly search for information and use this data to plan the maintenance of railway traffic lights.