Check patentability & draft patents in minutes with Patsnap Eureka AI!

Rainy-day video image separation method based on exclusiveness sparse coding

A video image and sparse coding technology, which is applied in image analysis, image enhancement, image coding, etc., can solve problems such as difficult to describe, and achieve the effect of clear video images in rainy days

Inactive Publication Date: 2018-08-10
GUANGDONG UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for rainy video images, it is difficult for people to obtain separate rain images in advance to initialize the rain dictionary, and there is no certain area in the rainy video image that is all rain, which can be extracted as the initialization of the dictionary. Therefore, it is very difficult It is difficult to learn two different dictionaries or systems for the rain layer and the image layer in the traditional way to describe the two layers of images and separate them

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
  • Rainy-day video image separation method based on exclusiveness sparse coding
  • Rainy-day video image separation method based on exclusiveness sparse coding
  • Rainy-day video image separation method based on exclusiveness sparse coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with specific embodiment:

[0047] See attached figure 1 As shown, a kind of rainy weather video image separation method based on mutually exclusive sparse coding described in this embodiment comprises the following steps:

[0048] S1. Extract image frames from the rainy day video image, and perform S2-S6 operations on each frame of image J.

[0049] S2. Initialize dictionary D 1 , the coding coefficient corresponding to the rain block and the real image block with Stacked matrix of rain blocks and the stacked matrix of real image patches Indicator variable w 1 .

[0050] S3. Utilize sparse approximation to update the encoding coefficients corresponding to the rain block and the real image block to obtain the latest encoding coefficients with

[0051] The specific process is:

[0052] The dictionary D obtained by the previous iteration 1 , the stacking matrix of rain blocks and image ...

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 a rainy-day video image separation method based on exclusiveness sparse coding. The method changes the real image and rain separation problem into the signal separation problem. In the separation process, a dictionary having exclusiveness is obtained in the continuous iterative learning process by utilizing intrinsic attribute difference between a real image layer and a rain layer and based on exclusiveness of constraint sparse coding coefficient, so that the rain layer in a rain video image is allowed to be gradually separated from the real image layer during iteration. The method achieves an effect of separation between the real image layer and the rain layer, and meanwhile, enables the rainy-day video image to be clearer.

Description

technical field [0001] The invention relates to the technical field of video image processing, in particular to a method for separating rainy weather video images based on mutually exclusive sparse coding. Background technique [0002] With the development of broadband network technology and the advancement of projects such as safe cities, video surveillance technology has been widely used in many fields such as education, government, security, transportation, sports, etc. The application scenarios are gradually increasing. Because the outdoor environment often needs to face severe weather such as rain and snow, and such severe weather conditions have inestimable damage to the characteristics of video images, such as the visibility and contrast of images in heavy fog will be seriously affected, and rain and snow may be Part of the image is caused to be blocked, which affects further processing of the image. [0003] Most of the existing materials deal with rainy weather vi...

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): G06T5/00G06T9/00
CPCG06T9/001G06T2207/10016G06T2207/30232G06T5/73
Inventor 罗玉凌捷王文冲
Owner GUANGDONG UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com