Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Train number automatic identification method and system

An automatic recognition system and automatic recognition technology, applied in the field of image recognition, can solve the problems of inconsistent grayscale of the same character, no analysis and processing, etc., and achieve the effect of saving processing time, reducing the degree of manual dependence, and achieving a high degree of intelligence.

Inactive Publication Date: 2017-06-06
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS +1
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It mainly solves the positioning problem of multi-line characters. There is no analysis and processing for the inconsistent gray level of the same character.

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
  • Train number automatic identification method and system
  • Train number automatic identification method and system
  • Train number automatic identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] The car number automatic identification system of this embodiment includes a camera 2, a light source 3, a wheel sensor 1 and a processing unit, and the installation diagram of the camera 2 and the light source 3 is as follows figure 2 As shown, camera 2 is a 5-megapixel industrial CCD camera with a delay time of 1500 μS and an exposure time of 2000 μS. The light source 3 is an LED flash light source. The single power of the light source 3 is 250W. There are 2 cameras 2 and 3 light sources respectively. The distance between the light source 3 and the ground is equidistant, the distances between the two cameras 2 and the ground are unequal distances, placed up and down, the width of the box 4 is 30cm, the height is 40cm, the height of the bottom of the box 4 is 2.6m from the ground, and the box 4 consists of a Supported by pillar 5, the processing unit is a vehicle number positioning and recognition system.

Embodiment 2

[0052] The on-site installation schematic diagram of the automatic vehicle number identification system of this embodiment is as follows image 3 As shown, the shooting device is installed on one side of the track, the camera 2 and the light source 3 are packaged in a closed box 4, the box 4 is supported by a pillar 5, and the distance between the pillar 5 and the center of the track is 2.8m, so The wheel sensor 1 transmits a trigger signal to the camera 2 and the light source 3, and the camera 2 transmits the image information to the processing unit.

Embodiment 3

[0054] The processing unit, that is, the workflow of the vehicle number positioning and recognition system is as follows: Figure 4 As shown, it is mainly divided into image preprocessing, rough positioning of vehicle number image, precise positioning of vehicle number image, tilt correction of vehicle number image, segmentation of vehicle number image and recognition of vehicle number image.

[0055] Specifically, the principle flowchart of the positioning system in the processing unit is as follows Figure 5 As shown, the steps include:

[0056] Step 1: Image preprocessing, crop the image according to the approximate area where the vehicle number appears to obtain the ROI area, extract the color components according to the difference between the color of the vehicle number and the background of the vehicle body, and turn the color image into a single-channel image;

[0057] Step 2: Use the local binarization method based on the mean and variance to eliminate some interferen...

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 train number automatic identification method and identification system. The system includes a camera, a light source, a wheel sensor and a processing unit, the wheel sensor transmits a triggering signal to the camera and the light source, and the camera transmits image information to the processing unit. The method provided by the invention includes the following steps: 1. image acquisition: after passing a line, wheels trigger the sensor to generate a signal, and the camera and the light source receives the signal to complete image acquisition; 2. train number positioning: the acquired image is preprocessed, coarse positioning and accurate positioning of the train number are performed, and thus train number positioning is completed; 3. train number identification: train number character segmentation is performed, the segmentation number (number) is recorded, and thus train number identification is completed; and 4. data transmission: train number positioning and identification results are transmitted to a terminal device to be stored and displayed. The train number automatic identification method and system can dynamically identify a moving train number, greatly reduce the manual work amount and a measuring error brought by manual work, and improve the accuracy rate and efficiency of train number identification.

Description

technical field [0001] The invention relates to the field of image recognition, more precisely, relates to an automatic vehicle number recognition system and method thereof in rail transit. Background technique [0002] At present, my country's railway operation mileage continues to expand, and railway traffic is increasingly developed. my country has become a major country in railway operation, and its stock ranks among the top in the world. The vehicle number is an important symbol of the vehicle, and plays an important role in dispatching, overhauling, vehicle marshalling, and vehicle tracking. The model number is painted on the body to form a number mark, which is used for manual identification of the model number. During daily maintenance, the process of extracting and storing the operating status of each component needs to use the vehicle model number as an index to achieve an accurate grasp of the overall situation; Call it out for comparison. The traditional car n...

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 Applications(China)
IPC IPC(8): G06K9/20G06K9/40G06K9/46G06T3/00G06K9/36
CPCG06V10/22G06V10/247G06V10/30G06V10/443G06V2201/09G06T3/147
Inventor 辛明远石峥映梅劲松黎宁郭其昌蒋银男曹蔡旻沈晓冬王辉平
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com