Electronic Science and Technology ›› 2022, Vol. 35 ›› Issue (8): 53-57.doi: 10.16180/j.cnki.issn1007-7820.2022.08.009

Previous Articles     Next Articles

Trackside Signal Light Recognition Based on Image Processing

FENG Junyi1,SHEN Tuo1,2,ZHANG Xuanxiong1   

  1. 1. School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China
    2. Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety,Tongji University,Shanghai 201804,China
  • Received:2021-03-09 Online:2022-08-15 Published:2022-08-10
  • Supported by:
    National Natural Science Foundation of China(U1734211)


The trackside signal light is one of the important components for prompt train operation. In order to ensure train operation safety, a method based on image processing technique is proposed to effectively locate the trackside signal light and identify its color information. The trackside signal light ROI is extracted through the empirical value, and then the color segmentation is carried out to the ROI in the RGB color space to avoid the influence of irrelevant background, and remaining noise is removed through morphology processing. Hough-circle transform is performed on the processed image for the extracted candidate region of signal light, and the operating trackside signal light related to the running train is located according to the position characteristics between the signal light and the track. The pixel value information in the signal light area is analyzed for signal color recognition. The experimental results indicate that the method can precisely locate and recognize trackside signals, and the color correction ratio is 91.42% for red, 85.00% for yellow, and 94.29% for green, respectively.

Key words: trackside signal light, image processing, morphology processing, color segmentation, edge detection, rail location, Hough transform, signal light recognition

CLC Number: 

  • TP391