Unlock instant, AI-driven research and patent intelligence for your innovation.

Low-illumination license plate image restoration method based on license plate tracking and frame accumulation optimization

A technology of license plate image and restoration method, which is applied in image enhancement, image data processing, instruments, etc., to achieve the effect of avoiding blur problems, suppressing low-light noise, and good restoration effect

Active Publication Date: 2016-02-24
NAT UNIV OF DEFENSE TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of low-illuminance license plate image restoration, the present invention provides a low-illuminance license plate image restoration method based on license plate tracking and frame accumulation optimization

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
  • Low-illumination license plate image restoration method based on license plate tracking and frame accumulation optimization
  • Low-illumination license plate image restoration method based on license plate tracking and frame accumulation optimization
  • Low-illumination license plate image restoration method based on license plate tracking and frame accumulation optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0024] The present invention provides a low-illumination license plate image restoration method based on license plate tracking and frame accumulation optimization. The method flow is as follows figure 1 As shown, including the following steps:

[0025] Step 1: Use the license plate tracking algorithm to separate the license plate image of the moving vehicle in the low-light video.

[0026] In the specific implementation process, first obtain a low-illuminance video, and use a tracking method based on sparse representation to separate the license plate image in each frame for the license plate image of the moving vehicle in the video. The observation vector y of the license plate image collected in the surveillance video is:

[0027] y=Ua+e=a 1 u 1 +a 2 u 2 +...+a n u n +e

[0028] Among them, U=[u 1 ,u 2 ,...,U n ] Is a set of bases used to represent the license pl...

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 field of image information processing, in particular to a low-light license plate image restoration algorithm based on license plate tracking and frame accumulation optimizing. The low-light license plate image restoration algorithm includes firstly adopting a target tracking algorithm, tracking the license plate in low-light videos, and separating license plate images from video frame images to obtain a license plate image sequence; performing frame accumulation of the license plate images and optimizing parameters of the license plate images by means of genetic algorithm, and improving restoration effect by the frame accumulation images. Compared with a conventional low-light license plate image restoration algorithm, the low-light license plate image restoration algorithm has the advantages that noise of the low-light license plate images can be effectively suppressed, signal to noise ratio is increased, more accurate license plate number edges can be obtained, and high-quality license plate source images can be provided for extraction and intelligent analysis of license plate information.

Description

Technical field [0001] The invention belongs to the field of image information processing and relates to a low-illumination license plate image restoration method. Background technique [0002] License plate image information is of great significance in the fields of security monitoring, intelligent transportation and social security. It plays a very important role in vehicle speeding supervision, car anti-theft, highway and parking lot charging, and traffic accident monitoring. However, the license plate images collected under low illumination conditions often have the characteristics of low signal-to-noise ratio, large noise, and complex noise components, which have a great impact on the extraction and analysis of license plate information, resulting in a decrease in the accuracy of license plate recognition and tracking. Therefore, it has important practical significance and practical application value to effectively denoise the noisy license plate image in low illumination en...

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 Patents(China)
IPC IPC(8): G06T5/00
Inventor 徐玮尹晓晴张政刘煜王炜
Owner NAT UNIV OF DEFENSE TECH