Modern tramcar groove type track turnout automatic identification method and system

• Main Authors: ZHANG ZIYI, LIU XUAN, XIE YONGJUN, CHEN RENXING, LYU JINTAO, TIAN HAOTIAN, LI ZHENSEN
• Format: Patent
• Language: Chinese; English
• Published: 29.08.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses an automatic identification method and system for a groove-type track turnout of a modern tramcar, and the method comprises the following steps: decomposing a groove-type track video stream frame by frame, and carrying out the image preprocessing, thereby obtaining a preprocessed groove-type track turnout image; an image detection network is constructed and trained based on the YOLOv5 network, the image detection network comprises an input end, a backbone network, a feature fusion part and a regression function, the input end adopts an image input end of the YOLOv5 network, the backbone network adopts a PP-LCNet model, the feature fusion part adopts a bidirectional weighted feature pyramid network, and the regression function adopts an EIoU loss function; and marking the turnout type of the image to form an image data set, and inputting the newly collected image of the groove type track turnout into the trained image detection network to obtain a turnout marking block diagram and the t