Dynamic video road license plate identification method

A license plate recognition and video technology, applied in the field of license plate recognition on road video, can solve the problems of slow license plate recognition, low character recognition accuracy, and difficulty in positioning and recognition algorithms to support all-weather light lines, achieving high recognition accuracy. , The effect of saving case handling time

Inactive Publication Date: 2017-08-18
EAST CHINA NORMAL UNIV
View PDF1 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method aims to solve the defects of low character recognition accuracy, slow license plate recognition speed, low license plate positioning accuracy in complex road environments, and difficulty in supporting all-weather light lines in positioning and recognition algorithms in the existing technology, and improve the speed of searching vehicle trajectories. and police efficiency

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
  • Dynamic video road license plate identification method
  • Dynamic video road license plate identification method
  • Dynamic video road license plate identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0098] Such as image 3 As shown, it is a screenshot of a single image recognition process. The original image (a) has been down-sampled and grayscaled (b) to reduce the image resolution to about 400*600, which can reduce the image resolution while not damaging the useful information in the image. The number of calculation points, thereby reducing time consumption. The collected image is an RGB color model, with a large amount of data and a variety of colors, which is not conducive to the rapid processing of the image. Therefore, the color image is converted into a grayscale image, so that the subsequent algorithm can be better realized. The weighted average method is adopted: namely: 0.2989×R+0.5870×G+0.1140×B.

[0099] The top-hat transformation (c) is the difference between the original image and the opening operation. The opening operation enlarges the crack or the local low-brightness area, and subtracts the image after the opening operation from the original image. Are...

Embodiment 2

[0110] Such as Figure 4 As shown, the license plate recognition effect of the above steps is performed for the frame image extracted from the road dynamic video. Among them, (a) video screenshot (b) image extraction from video (c) downsampling and grayscale (d) top hat transformation (e) edge detection (f) removal of long background edges and small edge noise (g) Closed operation (h) Connected domain marking method (i) Locating license plate (j) Extracting license plate image, binarizing license plate image (k) Image filtering (l) Cutting license plate and normalizing license plate characters (m) License plate character recognition.

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 dynamic video road license plate identification method. Through extracting roadside dynamic vehicle monitoring videos to realize automatic license plate number identification and record, the information and the locus information of vehicles can be conveniently tracked; the information is acquired through multiple cameras, image pre-processing, license plate area positioning, license plate character segmentation and HDRBM character identification of the frame image information acquired from video flows are carried out, identified license plates are saved to a text according to camera numbers, license plate numbers and the monitoring time, the search-needing license plate numbers are ordered according to the time sequence, the cameras through which the vehicles pass can be acquired according to the camera number information, the locus of the vehicles can be tracked according to the road information of the cameras. The method is advantaged in that license plate positioning under the complex background environment can be satisfied, a high character identification rate is realized, and demands for searching the target vehicles on roads can be satisfied.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and artificial intelligence, and in particular relates to a method for performing license plate recognition on road videos. Background technique [0002] With the rapid development of my country's urban economy, the scale of cities continues to expand, and the urban population continues to grow. The factors that affect road traffic safety, such as people, vehicles, environment, and management brought about by urbanization and motorization, have become more complex. China's urban traffic problems increasingly prominent. The traditional way of traffic supervision has been difficult to meet the requirements of the modernization of supervision, introducing new technology and improving the efficiency of supervision is undoubtedly one of the important ways to solve the problem. At home and abroad, the intelligent transportation system has become an important direction of the current tra...

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): G06K9/32G06K9/34G06K9/62
CPCG06V20/62G06V30/153G06V20/625G06V30/10G06F18/2415
Inventor 黄鹤郑正奇
Owner EAST CHINA NORMAL UNIV
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