Motor vehicle license plate synthetic data generation method

A technology for synthesizing data and motor vehicles, applied in the field of intelligent transportation, can solve the problems of incomplete coverage, small amount of data in the license plate data set, inaccurate data labeling, etc., to improve collection and generation efficiency, high degree of authenticity, and reduce differences Effect

Active Publication Date: 2019-11-26
UNIV OF SCI & TECH OF CHINA
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Problems solved by the technology of the present invention: In order to solve the problems of small amount of data, inaccurate data labeling, and incomplete coverage of license plate data sets currently used for deep learning training, a method for generating synthetic data of motor vehicle license plates is provided to obtain more comprehensive coverage data; reduces the discrepancy between synthetic and real image domains

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
  • Motor vehicle license plate synthetic data generation method
  • Motor vehicle license plate synthetic data generation method
  • Motor vehicle license plate synthetic data generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The specific implementation manners of the present invention will be described below in conjunction with the accompanying drawings.

[0046] First the nouns appearing in the present invention are explained:

[0047] License plate data: Indicates the components of the license plate data set, generally represented by images, and sometimes refers to the scene containing the license plate;

[0048] License plate image data: Indicates the license plate data in the form of images, focusing on images;

[0049] License plate data content: Indicates the content of the license plate data, including characters on the license plate, base plate, vehicle type, and light source type;

[0050] Synthetic license plate data: Indicates artificially synthesized license plate data.

[0051] Such as figure 1 As shown, the present invention provides a method for generating synthetic data of a motor vehicle license plate as follows: first, carry out highly simulated three-dimensional modeli...

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 relates to a motor vehicle license plate synthetic data generation method, which comprises the following steps: firstly, obtaining a license plate font from an official public specification file and modeling to enable the synthetic license plate data to be close to the condition of a real license plate; secondly, utilizing a virtual engine to construct a scene, carrying out omnibearing rendering, generating annotations automatically, and improving the collection and generation efficiency of a data set; thirdly, setting diversified license plate generation conditions in the aspects of weather, illumination, distance, angle and the like, and obtaining data with more comprehensive coverage; and finally, performing style migration on the generated synthetic license plate data byusing a style migration technology, so that the difference between an artificially synthesized image and a real image domain is reduced.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation, and in particular relates to a method for generating synthetic data of motor vehicle license plates, which can be applied to the detection and recognition of license plates in intelligent transportation systems. Background technique [0002] With the development of video surveillance technology and deep learning technology, the intelligent transportation system has become the development direction of the future transportation system, which can alleviate the increasing urban traffic congestion, reduce traffic violations and vicious traffic accidents, and provide a solution for various traffic accidents and The post-processing of personal and property safety provides strong evidence. In this process, the license plate number plays a vital role as the unique identity of the motor vehicle, so the detection and recognition of the license plate is an important part of the intelligent...

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): G06T17/00G06T15/00G06T15/50G06K9/32G06K9/34G06N3/04G06N3/08
CPCG06T17/00G06T15/005G06T15/506G06N3/084G06V20/63G06V10/267G06V20/625G06N3/045
Inventor 王子磊靳路康
Owner UNIV OF SCI & TECH OF CHINA
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap