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

Image Dehazing Method with Adaptive Global Dark Channel Prior for Bright Regions

A bright area, self-adaptive technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of Halo phenomenon, such as high computational complexity and failure

Inactive Publication Date: 2018-04-06
GUILIN UNIV OF AEROSPACE TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0019] In view of the failure of the dark channel prior defogging algorithm for bright areas, and the problems of block effect, Halo phenomenon and high computational complexity in obtaining dark channel by blocks, the present invention proposes an adaptive global dark channel prior for bright areas. defogging method

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 Dehazing Method with Adaptive Global Dark Channel Prior for Bright Regions
  • Image Dehazing Method with Adaptive Global Dark Channel Prior for Bright Regions
  • Image Dehazing Method with Adaptive Global Dark Channel Prior for Bright Regions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] The fuzzy domains of the two input variables are normalized to the [0, 1] range, and the domains of the output variables K and ω are [0.2, 0.6] and [0.6, 1] respectively; except that the input variable P adopts Gaussian membership Except for degree function, other variables are described by triangular or trapezoidal membership function.

[0079] The fuzzy logic rules are shown in Table 1. The language values ​​of each input and output variable are set to three, which are S, M and B respectively. S represents small, M represents medium, and B represents large. There are 9 fuzzy logic rules in the table. Rules 1-3 indicate that when the P value is small, that is, the fog concentration is high, the output tolerance K is small and the adjustment factor ω is large regardless of the coverage of the bright area; Rules 7-9 indicate that the P value is large, which means that the fog is thin and the image contrast is better. The values ​​of K and ω are mainly determined by the i...

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 adaptive global dark primary color prior dehazing method for bright areas includes the following steps: Step 1: Obtain the global dark primary color value of the hazy image I(x); Step 2: Establish a fuzzy logic controller to obtain the tolerance parameters and transmittance adjustment factor; Step 3: Use tolerance parameters to divide the hazy image into bright areas and non-bright areas; Step 4: Find the atmospheric light intensity; Step 5: Find the transmittance; Step 6: Use tolerance The difference parameters, transmittance and atmospheric light intensity are used to obtain the restored image. This method can effectively solve the problems of block effect, Halo phenomenon and color distortion caused by bright area distortion and blocking processing. It can obtain better defogging effect without increasing exposure processing, and the image contrast, information entropy and The objective evaluation results of the three aspects of average gradient are significantly better than other comparison algorithms, and the computing efficiency is also greatly improved.

Description

technical field [0001] The invention relates to digital image processing, in particular to model-based image fog, and more specifically to an adaptive global dark channel prior defogging method for bright regions. Background technique [0002] There are many types of model-based image defogging algorithms, which can be divided into two types: the defogging method based on multiple images and the defogging method based on a single image according to the different processing objects. The former method estimates the properties of the propagation medium by comparing and analyzing multiple images of the same scene under different weather conditions, so it has high requirements on the imaging system and is not suitable for real-time processing; while the defogging algorithm based on a single image can adapt to Various applications have become the hotspot of current research. Tan et al achieved the purpose of dehazing by maximizing the local contrast of the restored image [1] , b...

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 Patents(China)
IPC IPC(8): G06T5/00G06T5/40
CPCG06T5/40G06T2207/20004G06T5/73
Inventor 邓莉李欧迅赵素文孙山林嵇建波杨双周菊瑄陈锡华梁强张文凯王勇军盘书宝张绍荣
Owner GUILIN UNIV OF AEROSPACE TECH
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