Image defogging method and device

An image and foggy technology, applied in the field of image processing, can solve the problems of white borders extended by depth jumps, overall dark images, etc., and achieve the effect of strong ability, bright colors, and multiple layers

Active Publication Date: 2016-05-11
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF5 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention provides a method and device for image defogging to solve the problem of image defogging methods provided by the prior art. Problems with phenomena such as extended white borders

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 and device
  • Image defogging method and device
  • Image defogging method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] figure 1 The implementation flow of the image defogging method provided by Embodiment 1 of the present invention is shown, and the details are as follows:

[0079] In step S101 , artificially add fog to the fog-free image to generate a fog-containing image.

[0080] In the embodiment of the present invention, for a foggy image, it is difficult to obtain its corresponding fog-free image for training. In order to solve this problem, the embodiment of the present invention adopts the artificial fogging method to add fog to the non-fogged image to produce a foggy image.

[0081] One advantage of using artificially fogged images is that the transmittance of foggy images can be easily obtained for the training of multi-scale deep convolutional networks.

[0082] Among them, the scene depth of the fog-free image and the set fog concentration can be obtained first, and then the fog concentration and the scene depth can be converted into transmittance, and finally according to...

Embodiment 2

[0117] Figure 6 A specific structural block diagram of the image defogging device provided by Embodiment 2 of the present invention is shown. For convenience of description, only parts related to the embodiment of the present invention are shown. The image defogging device 6 includes: a manual fogging unit 61 , a model training unit 62 , a transmittance output unit 63 and an image defogging unit 64 .

[0118] Wherein, the artificial fogging unit 61 is used for artificially fogging the non-foggy image to generate the foggy image;

[0119] A model training unit 62, configured to input the foggy image and the transmittance of the foggy image to a deep convolutional network or a multi-scale deep convolutional network, and train the deep convolutional network or the multi-scale deep convolutional network, until the error between the transmittance output by the deep convolutional network or the multi-scale deep convolutional network and the transmittance of the foggy image is less...

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 is suitable for the technical field of image processing and provides an image defogging method and device. The method comprises the steps of: carrying out manual fog addition on an image free from fog so as to generate a fogged image; inputting the fogged image and the transmissivity of the fogged image into a depth convolution network or a multi-scale depth convolution network, and training the depth convolution network or the multi-scale depth convolution network until an error between the transmissivity output by the depth convolution network or the multi-scale depth convolution network and the actual transmissivity of the fogged image is lower than a preset error threshold value; inputting the fogged image to be defogged into the trained depth convolution network or multi-scale depth convolution network, and outputting the transmissivity of the fogged image; and recovering the fogged image into a defogged image according to a foggy weather imaging model, an atmosphere light value and the transmissivity of the fogged image. The image defogging method and device are capable of substantially reducing the occurance of a white edge phenomenon and improving the contrast ratio greatly.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image defogging method and device. Background technique [0002] In foggy weather, in addition to water molecules, there are aerosol particles and water droplets in the air, which attenuate and absorb light. The acquired images and videos have low definition, decreased contrast, overall grayish white color, color shift and color distortion. [0003] Image defogging technology can significantly improve the clarity of degraded images, enhance contrast, and correct color deviation. [0004] The current mainstream dark channel prior image defogging algorithm is based on the statistical law of a large number of clear outdoor images, that is, the pixel value of at least one color channel in the non-sky local area of ​​most clear images is very low and tends to 0, however, the dark channel prior has its own limitations. The dark channel prior is not valid in the...

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): G06T5/00
CPCG06T5/003G06T2207/10004G06T2207/10024G06T2207/20182
Inventor 乔宇朱细妹
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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