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

Deep learning-based single-image de-fogging method

A single image and image technology, applied in the field of single image dehazing based on deep learning, to achieve the effect of good dehazing effect, improved peak signal-to-noise ratio, and fast processing speed

Active Publication Date: 2017-12-08
PEKING UNIV SHENZHEN GRADUATE SCHOOL
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a new image defogging method to solve the problem of restoring aerial video images in haze weather to high-definition fog-free images

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
  • Deep learning-based single-image de-fogging method
  • Deep learning-based single-image de-fogging method
  • Deep learning-based single-image de-fogging method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0025] The present invention takes the video obtained by drone aerial photography in foggy weather as an example. First, the image of each frame in the video is taken out, and the RGB image with a resolution of 3840×2160 is used as the input of the method of the present invention, and the method will automatically extract the R channel in R, G, and B to form a two-dimensional grayscale image. The specific treatment is as follows (such as figure 1 ):

[0026] A. The scattering effect is eliminated, and the The implementation method is:

[0027] A1. The input data I of this step is subjected to convolution Conv1 operation, where Conv1(I)=W 1 I+B 1 ;W 1 is the parameter of the convolutional layer neuron, B 1 is the offset.

[0028] A2. Perform the ReLU operation on the value of each pixel of t...

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 deep learning-based single-image de-fogging method and belongs to the image processing field. According to the method of the invention, a formula J(x,y)=I(x,y)1 / T(x,y)+A(1-1 / T(x,y) is inferred through transformation according to the formula I(x,y)=T(x,y)J(x,y)+(1-T(x,y))A; and a deep convolution neural network technique is adopted to obtain a high-definition J(x, y). The method of the invention has a good de-fogging effect. According to the method of the invention, matrix addition operation is adopted, so that the processing speed of the method is high.

Description

technical field [0001] The invention provides a method for defogging a single image, in particular to a method for defogging a single image based on deep learning. Background technique [0002] The impact of smog on drone aerial photography operations cannot be underestimated. The images formed by aerial photography in foggy weather are blurred, and the information that people need to capture is lost. With the deterioration of the air condition, the demand for defogging of UAV aerial images is getting higher and higher. [0003] The problem of image defogging belongs to the problem of image restoration, which cannot be solved by simple image enhancement technology. According to McCartney's fogging model (E.J.McCartney, "Optics of the atmosphere: scattering bymolecules and particles," New York, John Wiley and Sons, Inc., 1976.421p., 1976.), the scene in the original scene is through the air The water droplets or microparticles are captured into the lens after refraction or...

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): G06T5/00G06T5/50
CPCG06T5/50G06T5/73
Inventor 邹月娴陈泽晗王毅
Owner PEKING UNIV SHENZHEN GRADUATE SCHOOL
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