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
CN109948419AInactive Publication Date: 2019-06-28上海眼控科技股份有限公司
4 Cites 5 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
上海眼控科技股份有限公司
Publication Date
2019-06-28
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

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