A design of railway intelligent obstacle detection system

Long Chen

doi:10.1117/12.2613665

10 November 2021 A design of railway intelligent obstacle detection system

Long Chen

Proceedings Volume 12050, International Conference on Smart Transportation and City Engineering 2021; 120503V (2021) https://doi.org/10.1117/12.2613665
Event: 2021 International Conference on Smart Transportation and City Engineering, 2021, Chongqing, China

Abstract

The advanced railway signal system can prevent train-to-train collision automatically under normal working conditions, but the lack of perception of obstacles in front of the train has always been the pain point of the existing signal system. In this research, a design of Railway Intelligent Obstacle Detection System (RIODS) is proposed for the detection and warning of obstacles on the track, such as pedestrians, rocks, and vehicles. RIODS is a comprehensive and effective system solution. By deploying the subsystem of RIODS in the vehicle, trackside, and control center to meet the engineering application needs in different operation scenarios, the availability of the system is greatly improved, and the dependence on the performance of a single sensor is reduced. Based on multi-sensor fusion technology, deep learning algorithms, train positioning technology, and wireless communication, the system achieves information collection and analysis, and obstacle detection. Through field testing, the expected design function has been achieved. RIODS can be applied to different environments, and effectively improves the safety of train operation

Citation Download Citation

Long Chen "A design of railway intelligent obstacle detection system", Proc. SPIE 12050, International Conference on Smart Transportation and City Engineering 2021, 120503V (10 November 2021); https://doi.org/10.1117/12.2613665

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available