Method for Precise Recognition of Train Forward Target Based on Recognition Model and Classification Model

A technology of recognition model and classification model, applied in the field of image recognition of unmanned driving systems, can solve the problems such as insufficient safety and reliability of train anti-collision warning or control information, difficulty in accurately identifying the train's forward target, and reducing train operation efficiency, etc. The effect of increasing the scope of application, reducing the calculation parameters and calculation load, and improving the recognition accuracy

Active Publication Date: 2022-03-08
BEIHANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Traditional visual processing methods are very limited, and it is difficult to accurately identify the forward target of the train. In practical applications, the efficiency of train operation will be greatly reduced, making the train anti-collision warning or control information not safe and reliable enough.

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
  • Method for Precise Recognition of Train Forward Target Based on Recognition Model and Classification Model
  • Method for Precise Recognition of Train Forward Target Based on Recognition Model and Classification Model
  • Method for Precise Recognition of Train Forward Target Based on Recognition Model and Classification Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0028] see figure 1 , Figure 3 ~ Figure 6 In the shown train image acquisition system, when the train is running, the long focal length camera 2 and the short focal length camera 3 simultaneously collect the video data of the forward direction of the train in real time, and then transmit the collected video data to the industrial computer for processing by the industrial computer Afterwards, it is transmitted to the unmanned driving control system, and the braking warning information is output through the unmanned driving control system.

[0029] see figure 2 As shown, the method for accurately identifying the forward target of the train based on the recognition model and the classification model of the present invention has been completed in the industrial computer of the train, and the method includes the following steps:

[0030] Step 1: install multi...

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 invention discloses a method for accurately identifying a forward target of a train based on a recognition model and a classification model, comprising: a step of collecting video data of the forward train by cameras with long and short focal lengths; Processing steps; finally output the target image to the driverless control system. After being processed by the method of the present invention, the train in front and other obstacles that affect driving safety can be effectively identified to provide brake protection control, or to provide reliable brake warning information for the driver, thereby effectively avoiding damage caused by equipment failure or human error. Operational accidents such as rear-end collision, side impact or signal violation.

Description

technical field [0001] The present invention relates to the technical field of image recognition for unmanned driving systems. Specifically, the present invention relates to a vision-based, recognition model and classification model-based method for precise recognition of train forward targets. Background technique [0002] With the rapid development of modernization, urban rail transit technology is becoming more and more mature. An unmanned driving system for urban rail transit based on signal control has been developed. In the case of normal operation of the system, even unmanned driving can ensure the stability and safety of the train. However, in emergency scenarios such as signal system failures, manual intervention is still required, so abnormal scenarios are also a high incidence of unmanned system train operation accidents. Since there is still a lot of room for improvement in the safety, reliability, usability and unmanned level of the unmanned driving system in ...

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): G06V20/58G06V20/40G06V10/25G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V20/41G06V20/56G06V10/25G06N3/045G06F18/2414G06F18/2431
Inventor 徐国艳熊绎维
Owner BEIHANG UNIV
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