Analysis of models for image processing when implementing an object detection system on a railway track

Journal Title: Modern Innovations, Systems and Technologies - Year 2021, Vol 1, Issue 1

Abstract

With the development of the railway industry, informatization of society and the automation of many technological processes, it becomes possible to create an automatic control system, diagnostics and safety of locomotive movement. One of the most important systems of this complex is the system for detecting objects on railway tracks, ruptures of the railway bed and its turns. Such a system can be developed in the form of a camera installed on a locomotive and information processing systems on board each rolling stock, or a global system for remote processing of information from several locomotives. Regardless of the implementation of the system, there is a need to create a block for detecting objects on images coming from cameras. The implementation of this block is possible using interacting full-convolutional and convolutional neural networks and training on a dataset covering various situations occurring on the railway tracks.

Authors and Affiliations

A. T. Tisetsky

Keywords

Related Articles

The problem of the lack of a unified reference application for the labeling system of medicines

A few years ago, an experiment on the labeling of medicines began in Russia. The rapid development of this experiment forced participants in the circulation of medicines to face a number of difficulties. This is caused b...

Changes in the quality indicators of shirt fabrics with different fiber compositions

The quality of textile fabrics is evaluated by physical, mechanical, consumer and hygienic properties. The durability of a fabric is also characterized by its resistance to abrasion. In turn, this durability and breathab...

Underwater optical wireless communication as a means of improving the efficiency of information and telecommunication support for deep-sea research

Sonar, radio frequency and optical wave systems are technologies that are used today to carry out underwater wireless communication. However, due to the need to deliver a large number of video images from autonomous unin...

Security of human private life when interacting with generative artificial intelligence

This scholarly article critically examines the intricate dynamics of personal privacy in the age of pervasive internet use, emphasizing the escalating challenges posed by Generative Artificial Intelligence. Every year th...

Analysis of the diameter of the pins of the drum of a cotton-cleaning unit on the efficiency of cleaning raw cotton

The article presents the results of increasing the efficiency of cleaning raw cotton based on the use of improving the design of the cotton cleaning unit. In the zone of cleaning raw cotton from small weeds, a peg drum w...

Download PDF file
  • EP ID EP706124
  • DOI https://doi.org/10.47813/2782-2818-2021-1-1-43-51
  • Views 177
  • Downloads 0

How To Cite

A. T. Tisetsky (2021). Analysis of models for image processing when implementing an object detection system on a railway track. Modern Innovations, Systems and Technologies, 1(1), -. https://europub.co.uk/articles/-A-706124