Multi-vehicle-license-plate dynamic identification method of real-time traffic scene

A real-time traffic and dynamic recognition technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the problems of external environmental factors, license plate recognition errors, license plate extraction errors, etc., to overcome uncertainty and achieve accurate The effect of improving performance and efficiency

Inactive Publication Date: 2018-09-07
合肥湛达智能科技有限公司
View PDF8 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a real-time traffic scene multi-license plate dynamic recognition method to solve the problem that the license plate recognition proposed in the above background

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
  • Multi-vehicle-license-plate dynamic identification method of real-time traffic scene
  • Multi-vehicle-license-plate dynamic identification method of real-time traffic scene
  • Multi-vehicle-license-plate dynamic identification method of real-time traffic scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0046] see Figure 1-3

[0047] Such as figure 1 As shown, the multi-license plate dynamic recognition method of a real-time traffic scene according to the present invention is composed of a convolutional neural network for license plate location and a convolutional neural network for license plate character recognition, which can efficiently locate and identify in real time Multiple license plates in a single image.

[0048] First construct the sample set an...

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 multi-vehicle-license-plate dynamic identification method of a real-time traffic scene. The method is mainly divided into the multiple main steps of image pre-processing, vehicle-license-plate locating network training, image post-processing, identification network training and the like. Multiple pieces of vehicle-license-plate information in a single picture can be highly efficient identified in real time by using a vehicle-license-plate locating network and a character identification network in a case of not dividing character information; and compared with traditional character segmentation and identification methods, the method of the invention has innovative advantages, and can be widely applied to parking lot charging and peccancy behavior monitoring of expressways and the like.

Description

technical field [0001] The invention relates to the technical field of machine vision and image processing, in particular to a method for dynamic recognition of multiple license plates in real-time traffic scenes. Background technique [0002] In recent years, with the rapid development of the field of intelligent transportation, the research on automatic license plate recognition algorithm has attracted more and more attention. Automated, fast, accurate and powerful license plate recognition system has become the demand of traffic control and traffic law enforcement. [0003] The traditional license plate recognition method is mainly divided into three steps: license plate area positioning, license plate character segmentation, and character recognition, all of which are based on a single license plate in a single image. Prior art CN107220638A discloses a license plate detection and recognition method based on deep learning convolutional neural network. Its main contents i...

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
IPC IPC(8): G06K9/32G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06V20/63G06V20/625G06F18/24G06F18/214
Inventor 张中牛雷
Owner 合肥湛达智能科技有限公司
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