A method and system for intelligent station announcement verification based on moving image recognition

A technology of moving image and verification method, which is applied in the field of intelligent station announcement verification based on moving image recognition, can solve the problems of inability to verify each other, wrong station announcement of the train station announcement system, and no station announcement, etc., to reduce the amount of calculation , reduce memory usage and improve reliability

Active Publication Date: 2022-06-24
SHENZHEN TONGGUANG TRACK TRAFFIC TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, once a communication failure occurs, the train station reporting system will have accidents such as station reporting errors and no station reporting. In the current PIS system, station reporting methods are divided into ATS station reporting, semi-automatic station reporting, manual station reporting, or relying on TMS. Data, or manual operation, the two cannot be mutually verified, and it is easy to cause other operational accidents

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and system for intelligent station announcement verification based on moving image recognition
  • A method and system for intelligent station announcement verification based on moving image recognition
  • A method and system for intelligent station announcement verification based on moving image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below through specific embodiments.

[0043] The invention proposes an intelligent station announcement verification method based on moving image recognition, which can perform deep neural network learning according to the collected images, predict the arrival station in advance, and perform mutual verification with the voice broadcast station, so as to avoid reports caused by communication failures. Station errors, improve the reliability of the station reporting system.

[0044] like figure 1 , is a kind of intelligent station announcement verification method based on moving image recognition provided by the embodiment of the present invention, specifically includes:

[0045] A method for verifying an intelligent station announcement based on moving image recognition, comprising the following steps:

[0046] S101: Detecting the train speed and acceleration, in response to the train speed and acceleration meeting the fi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention proposes an intelligent station announcement verification method based on moving image recognition. Firstly, the train speed and acceleration are detected, and in response to the train speed and acceleration meeting the first setting condition, the image acquisition terminal is triggered to obtain the train's traveling process. image; in response to the train speed and acceleration meeting the second set condition, stop the image acquisition operation to obtain the image set; input the image set into the trained neural network model to predict the arrival site; combine the predicted arrival site with the pre-stored The arrival site in the voice broadcast is matched to complete the verification; the method provided by the invention can carry out deep neural network learning according to the collected images, predict the arrival site in advance, and perform mutual verification with the voice broadcast site to avoid communication failures The station reporting errors caused by the system improve the reliability of the station reporting system.

Description

technical field [0001] The present invention relates to the field of train station announcement, in particular to an intelligent station announcement verification method and system based on moving image recognition. Background technique [0002] At present, the subway signal system uses the automatic train control system based on communication. The subway station announcement system is a part of this system, which is supported and operated by this system. The subway train operation is controlled by computer and runs strictly according to the speed curve to achieve high accuracy. Therefore, for the daily operation planning of the subway, the subway trains strictly follow the operation timetable, that is, when the train is running on the main line, a specific time in the timetable corresponds to the corresponding stop station, and the operation control of the subway The center plans the running timetable in a unified way, and sends it to each train through the wireless communi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/75G06V10/80G06V10/82G06N3/04G06N3/08G06T5/00
CPCG06T5/003G06T5/006G06N3/08G06T2207/20081G06T2207/20084G06N3/045G06F18/22G06F18/253
Inventor 张有利焦奕
Owner SHENZHEN TONGGUANG TRACK TRAFFIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products