Vehicle annual survey label detection method and device

A label detection and labeling technology, applied in image data processing, instrument, character and pattern recognition, etc., can solve the problems such as the inability to accurately detect the specific shape of the annual inspection label, and the inability to detect and identify the specific type of the annual inspection label, so as to improve the detection accuracy. The effect of improving the detection efficiency and reducing the monitoring pressure

Inactive Publication Date: 2018-06-29
SUZHOU KEDA TECH
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above image processing method cannot accurately detect the specific shape of the annual inspection label, that is, it cannot detect and identify the specific type of the annual inspection label

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
  • Vehicle annual survey label detection method and device
  • Vehicle annual survey label detection method and device
  • Vehicle annual survey label detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] This embodiment provides a method for detecting vehicle annual inspection labels, which is mainly applied to video monitoring of vehicle annual inspection labels on roads. Such as figure 1 shown, including the following steps:

[0079] Step S11 , acquiring an image to be inspected that includes an annual inspection label.

[0080] Specifically, such as figure 2 As shown, in the present embodiment, step S11 comprises the following steps:

[0081] Step S111, acquiring the area where the front window of the vehicle is located in the vehicle monitoring image. Specifically, in this embodiment, the method of statistical machine learning is used to roughly locate the position of the front window in the vehicle monitoring image. Of course, other positioning methods are also applicable to the present invention.

[0082] Step S112, performing grayscale processing on the area where the front window of the vehicle is located, so as to perform edge detection on the area where ...

Embodiment 2

[0134] This embodiment provides a vehicle annual inspection label detection device, such as Image 6 As shown, it includes an image acquisition unit 21 to be inspected, an annual inspection label position acquisition unit 22 , a calibration point detection unit 23 and a first determination unit 24 . in,

[0135] The image to be detected acquisition unit 21 is used to obtain the image to be detected that includes the annual inspection label;

[0136] The annual inspection label position acquisition unit 22 is used to utilize the pre-trained multi-level CNN network model to detect the image to be detected step by step, and obtain the frame position containing the annual inspection label as the position of the annual inspection label;

[0137] The calibration point detection unit 23 is used to detect the calibration points of the district frame containing the annual inspection label, wherein the calibration point represents the corner point on the outline of the annual inspectio...

Embodiment 3

[0152] This embodiment provides an example of the vehicle annual inspection label detection method provided in the first embodiment above. Include the following steps:

[0153] Step 1. Data collection

[0154] 1.1 Collect several image samples including front windows in the monitoring image.

[0155] 1.2 Mark the area of ​​each annual inspection label in the front window, and use the four corners of the rectangular and diamond-shaped annual inspection labels as key points.

[0156] 1.3 Obtain the entire area of ​​the annual inspection label along the upper, left, and right boundaries of the car window as a training sample. This area includes all annual inspection labels and some non-annual inspection labels.

[0157] 1.4 Randomly extract negative samples, positive samples, partial samples and calibration point samples from the training samples, the ratio is 3:1:1:2 respectively, the first layer of randomly collected sample scale is 12*12 pixels, and the second layer is 24* ...

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 the technical field of video surveillance and discloses vehicle annual survey detection method and device, wherein the method comprises the following steps: acquiring a to-be-detected image including an annual survey label; detecting the to-be-detected image step by step by using a pre-trained multistage CNN network model to obtain the position of an area box including anannual survey label to be taken as the position of the annual survey label; performing fixed point detection on the area box including the annual survey label, wherein the fixed point represents an angular point on the contour of the annual survey label; when no fixed point is detected, determining the annual survey label as an elliptical label; and when the fixed point is detected, determining the annual survey label as a rectangular label or rhombic label, wherein the area formed between the fixed points is the exact position of the annual survey label. According to the invention, on the basis of acquiring the position of the annual survey label, the area box, where the annual survey label is positioned, is subjected to fixed point detection to judge the type of the annual survey label,and thus the surveillance pressure of the traffic control department is effectively relieved.

Description

technical field [0001] The invention relates to the technical field of video surveillance, in particular to a method and device for detecting a vehicle annual inspection label. Background technique [0002] With the development of the economy and the continuous improvement of people's living standards, the number of motor vehicles on the road continues to increase, and a large number of motor vehicles are driving on the road, which undoubtedly brings huge management pressure to the traffic management department. At present, the statistical analysis of vehicle data is mainly achieved by installing surveillance cameras on the road, such as capturing vehicles running red lights and analyzing vehicle trajectories through images captured by surveillance cameras. [0003] However, the technology for judging whether a vehicle has submitted its annual inspection on time is still immature, and it often needs to be judged manually, which still requires a lot of manpower and energy. ...

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): G06K9/32G06K9/34G06T7/13
CPCG06T7/13G06V10/25G06V10/267
Inventor 周延培张安发黑光月陈燕娟陈曲史宁张剑覃明贵
Owner SUZHOU KEDA TECH
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