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

A real-time dehazing method for traffic video based on dark channel prior

A dark primary color prior, video technology, applied in image data processing, instruments, calculations, etc., can solve problems such as limitation, flicker, and many parameters, and achieve the effect of improving visual effects

Active Publication Date: 2018-05-29
UNIV OF SCI & TECH OF CHINA
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the median filter is not a good edge-preserving filter algorithm, and a sudden change in the depth of field in a local area will produce a halo effect.
Moreover, there are many parameters in the algorithm, which cannot realize self-adaptive adjustment, and requires manual testing and adjustment, which is limited in practical application.
The article [6] proposes a method for quickly defogging YUV video data, but there is a brightness difference between each frame of this method, and the processed result will have flickering problems

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
  • A real-time dehazing method for traffic video based on dark channel prior
  • A real-time dehazing method for traffic video based on dark channel prior
  • A real-time dehazing method for traffic video based on dark channel prior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] Such as figure 1 Shown, the concrete realization steps of the present invention are as follows:

[0045] (1) The YUV format is directly converted into a downsampled RGB image

[0046] The present invention is aimed at high-definition traffic video, such as 1080P video, and the image size of each frame is 1920*1080. It is difficult to meet the real-time processing requirements by directly performing defogging processing on images of this size or larger. In the present invention, the 1080P YUV data to be processed is directly down-sampled into an RGB image, which is used by the dark channel prior defogging algorithm later. The NV12 format is one of the YUV420sp formats. Here is an example to convert it. The conversion formula is as follows:

[0047]

[0048] In the above formula, R, G, and B respectively represent the three channel values ​​of the RGB format image, and Y, U, and V represent the values ​​of the YUV format image components respectively. In the conver...

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 present invention relates to a method for real-time defogging of traffic video based on dark channel prior, which is divided into three stages: the first stage is to directly down-sample YUV data into RGB images, and calculate the atmospheric light value and transmission after down-sampling The second stage is to use the transmittance obtained in the previous stage to directly reconstruct the original YUV data into the YUV data after dehazing; the third stage is to perform contrast stretching on the YUV data after dehazing in the previous stage. The present invention can achieve a better defogging effect on traffic videos, and can achieve real-time processing on 1080P YUV videos; contrast stretching is performed on the processing results, further improving the visual effect, and improving the driver's safe driving and traffic monitoring system and other fields are of great significance and have important commercial value.

Description

technical field [0001] The invention relates to a method for real-time defogging of traffic video based on dark channel prior, and belongs to the technical fields of digital image processing and intelligent transportation. Background technique [0002] With the development of society, industrial production has caused serious pollution to the environment. Especially in the past two years, air pollution has been very serious. According to statistics from relevant departments, the air quality of 74 cities in the Beijing-Tianjin-Hebei region, the "Yangtze River Delta" and "Pearl River Delta" regions, municipalities directly under the central government, provincial capitals, and cities under separate state planning have reached air quality standards throughout the year. less than 40% of the days. Air pollution is mainly caused by excessive PM2.5, which makes the whole environment shrouded in severe smog. On the one hand, this kind of smog pollution is very harmful to the human ...

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 凌强朱学俊邓思斌李博伦李峰
Owner UNIV OF SCI & TECH OF CHINA
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