Image defogging method based on convolutional neural network and prior information

A technology of convolutional neural network and prior information, applied in the field of image defogging based on convolutional neural network and prior information, to achieve the effect of good robustness, real and natural images, and fast training speed

Active Publication Date: 2017-05-31
TIANJIN UNIV
View PDF3 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such methods need to increase their training and processing speed

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
  • Image defogging method based on convolutional neural network and prior information
  • Image defogging method based on convolutional neural network and prior information
  • Image defogging method based on convolutional neural network and prior information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The invention makes full use of the learning ability of the deep learning network framework and the effectiveness of the prior information of the foggy image, and invents an image defogging method based on the convolutional neural network and the prior information. The imaging model of foggy weather can be expressed as:

[0040] I(x)=J(x)t(x)+A(1-t(x)),

[0041] In the formula, I(x) is the image taken in foggy days, J(x) is the clear image, A is the global background light, and t(x)∈[0,1] is the medium transmittance. Media transmittance is a key factor for image defogging, and it is related to the depth of the shooting scene, which can be expressed as:

[0042] t(x)=exp(-βd(x)),

[0043] In the formula, β is the atmospheric attenuation factor, and d(x) is the scene depth. In order to recover a clear image, it is crucial to accurately estimate the medium transmittance of the image. The present invention conducts research on accurate estimation of medium transmittance...

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, which belongs to the technical field of image processing and computer vision, provides an image defogging method for eliminating a fog effect in an image effectively to realize image defogging based on depth learning and prior information. According to the image defogging method, an imaging model of foggy weather is expressed as follows: I(x)=J(x)t(x)+A(1-t(x)), wherein the I(x) expresses an image shot on a foggy day, the J(x) expresses a clear image, the A indicates global background light, and the t(x) belonging to a set of [0,1] indicates medium transmissivity; and the medium transmissivity is expressed as follows: t(x)=exp(-betad(x)), wherein the indicates an atmospheric attenuation factor and the d(x) expresses a scene depth. Estimation is carried out based on combination of a deep learning technology with foggy image prior information; and a clear image is restored based on an imaging model by using a reverse compensation technology. The image defogging method is mainly applied to an image processing occasion.

Description

technical field [0001] The invention belongs to the technical fields of image processing and computer vision, and relates to an image defogging method based on a convolutional neural network and prior information. Background technique [0002] There are suspended particles such as fog, haze, and dust in the air, so images taken in foggy weather often have degradation phenomena such as low contrast, blur, and color distortion. When foggy images are used in practical applications such as video analysis and assisted driving, they often show certain limitations. In recent years, image dehazing has become an active research direction in research fields such as computer applications and consumer photography. However, image dehazing remains a challenging ill-posed problem. [0003] In the past few years, many image dehazing methods have been proposed, which can be mainly divided into the following categories: methods based on auxiliary information, methods based on non-model, met...

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): G06T5/00G06N3/04
CPCG06N3/04G06T5/003G06T2207/10024G06T2207/20081
Inventor 李重仪郭继昌
Owner TIANJIN 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