Gradient domain-based single image defogging method

A single image, gradient domain technology, applied in image enhancement, image data processing, instruments, etc., can solve problems such as color distortion, dark result image, etc., achieve the goal of reducing the number of times, avoiding color distortion, and improving color fidelity Effect

Inactive Publication Date: 2017-09-08
SICHUAN UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a single image defogging method based on the gradient domain, which can effectively improve the problems of the darker result image and color distortion in the existing gradient domain defogging algorithm.

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
  • Gradient domain-based single image defogging method
  • Gradient domain-based single image defogging method
  • Gradient domain-based single image defogging method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0033] Such as figure 1 As shown, the present invention is a single image defogging method based on the gradient domain, which is characterized in that it mainly includes the following steps:

[0034] (1) Collect the original foggy degraded image, calculate the gradient G of the foggy degraded image and the corresponding transmittance map t; the gradient here includes the gradient in the horizontal direction and the vertical direction, and the calculation method of the transmittance map can be used as follows express:

[0035]

[0036] Among them, p represents the coordinates of the two-dimensional space, which refers to the position of the pixel in the image, the max() operation represents the maximum value operation median() represents the median filter operation, sv is the window size used by the median filter, W(p )=min(I(p))...

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 provides a gradient domain-based single image defogging method which belongs to the image defogging technology field, and solves the problems that a conventional gradient domain defogging method is low in execution efficiency, a result map is darker, the color distorts, etc. The gradient domain-based single image defogging method comprises the steps of firstly converting a fog-degraded image into the gradient domain, and obtaining a plurality of gradient domain enhanced images by enhancing the gradient domain image at different scales; then, constructing a brightness characteristic-based gradient stretching function according to a weber law, and applying the function at different scales to correct the gradient domain enhanced images; and finally, adopting a weighted fusion algorithm with the color recovery factors to fuse the reconstructed images to obtain a finally defogged image. The gradient domain-based single image defogging method of the present invention enables the definition and the color fidelity of the fog-degraded image to be improved effectively, and by being compared with the conventional gradient domain defogging method, enables the execution efficiency to be improved.

Description

technical field [0001] The invention relates to the fields of digital image processing and computer vision, in particular to a single image defogging method based on gradient domain. Background technique [0002] With the reduction of computer costs and the improvement of performance, cameras and computer vision systems have been widely used in target recognition and tracking, monitoring, intelligent navigation and other related fields. However, the key to the design of these systems is that the image acquisition device can capture high-quality and clear images. In foggy conditions, images collected outdoors will be affected by impurities such as suspended particles and aerosols in the atmosphere, resulting in blurring, decreased contrast, and color distortion. Serious repercussions came. Therefore, it is of great significance for the application of computer vision systems to explore the reasons for the degradation of foggy images and use image dehazing technology to impro...

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
CPCG06T2207/10024G06T2207/20032G06T2207/20221G06T5/73
Inventor 王明辉刘运李晗王跃杨慧婷黄丽殊侯腾
Owner SICHUAN 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