Research on driver machine interface recognition method of train control system based on YOLOv8

Ye Cheng; Kaicheng Li; Guodong Wei

doi:10.1117/12.3023990

14 February 2024 Research on driver machine interface recognition method of train control system based on YOLOv8

Ye Cheng, Kaicheng Li, Guodong Wei

Proceedings Volume 13018, International Conference on Smart Transportation and City Engineering (STCE 2023); 130181J (2024) https://doi.org/10.1117/12.3023990
Event: International Conference on Smart Transportation and City Engineering (STCE 2023), 2023, Chongqing, China

Abstract

DMI can reflect the operation status of on-board ATP of the train control system in real time, and the recognition of its display content is an important prerequisite for realizing the automatic test of on-board ATP. The existing identification DMI technology has incomplete identification types and low detection speed. In order to achieve a better detection effect and a certain degree of wide applicability, a DMI information recognition method based on the YOLOv8 instance segmentation model is proposed. This method improves the segmentation and classification accuracy of DMI interface information by improving the training strategy of the instance segmentation task, completes the extraction of text information by combining OCR technology, and achieves high-precision segmentation of the most restrictive speed profile by combining the Douglas-Peucker algorithm. The experimental results show that the method proposed in this paper can accurately extract all the useful information of the DMI interface, meet the needs of laboratory testing, and lay the foundation for automatic testing.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ye Cheng, Kaicheng Li, and Guodong Wei "Research on driver machine interface recognition method of train control system based on YOLOv8", Proc. SPIE 13018, International Conference on Smart Transportation and City Engineering (STCE 2023), 130181J (14 February 2024); https://doi.org/10.1117/12.3023990

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Detection and tracking algorithms

Human-machine interfaces

Image segmentation

Optical character recognition

Control systems

Image processing

Acquisition tracking and pointing

Show All Keywords

Keywords/Phrases

Search In:

Publication Years