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

An automatic auditing method for illegal parking based on deep learning

A technology of illegal parking and deep learning, applied to instruments, character and pattern recognition, computer components, etc., can solve problems that affect traffic safety, affect the image of the city, affect the city's roads and traffic environment, and achieve good robustness, The effect of reduced review time

Inactive Publication Date: 2019-06-28
上海眼控科技股份有限公司
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Illegal parking of motor vehicles will affect the image of the city, affect the city's roads and traffic environment, and park vehicles at will will affect the normal driving of other vehicles, and may cause traffic accidents and affect traffic safety. Therefore, illegal parking has always been the focus of the traffic police team

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
  • An automatic auditing method for illegal parking based on deep learning
  • An automatic auditing method for illegal parking based on deep learning
  • An automatic auditing method for illegal parking based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described below in conjunction with the accompanying drawings.

[0040] The present invention is mainly based on a scene segmentation module, a license plate recognition module and a rule judgment module.

[0041] The scene segmentation module mainly involves the training of the segmentation model. First, the scene data set needs to be collected for data labeling. Since the labeling of the segmentation is difficult and consumes manpower and material resources, the present invention adopts a transfer learning method for the training of the scene segmentation model:

[0042] Firstly, class balance amplification is performed on the obtained pictures;

[0043] Then, divide the amplified picture according to the ratio of 10:1, and detect and label the data of "10", that is, only need to mark the bounding box of the object, and mark the part of "1" to segment the data set, that is, it needs to be marked Outline the object;

[0044] Desi...

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 an automatic auditing method for illegal parking based on deep learning, and the method comprises the following steps: carrying out the photographing and evidence collection ofan illegal parking vehicle through employing a photographing and camera shooting device, wherein the evidence collection information comprises three evidence images: a license plate close-up image, acab close-up image, and a bill pasting image, and the evidence collection information further comprises license plate number information of the illegal parking vehicles; carrying out region segmentation on the three evidence images by utilizing a segmentation model; performing license plate recognition on the segmented license plate area; judging whether the identified license plate number is thesame as the license plate number in the evidence collection information or not; judging whether the result area obtained through segmentation conforms to the screening principle or not, and giving out a final auditing result. According to the invention, the police is saved, and the illegal auditing efficiency and accuracy are improved.

Description

technical field [0001] The invention relates to the technical field of automatic verification of illegal parking in a traffic violation verification system, in particular to an intelligent verification method for illegal parking using deep learning. Background technique [0002] Illegal parking of motor vehicles will affect the image of the city, affect the city's roads and traffic environment, and park vehicles at will will affect the normal driving of other vehicles, and may cause traffic accidents and affect traffic safety. Therefore, illegal parking has always been the focus of the traffic police team . Snapping illegal parking is one of the effective remediation methods, but the snapshots must meet certain rules and requirements before they can be used as effective evidence of parking violations. Therefore, the review of illegal parking snapshots is very important. [0003] The current review method is purely manual review. This review method is inefficient, wastes pol...

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): G06K9/00G06K9/32G06K9/62
Inventor 周康明
Owner 上海眼控科技股份有限公司
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