Image defogging method based on multi-scale dense connection network

A connected network, multi-scale technology, applied in the field of image dehazing based on multi-scale densely connected networks, can solve the problems of reduced dehazing performance, limited robustness, poor effect, etc., to improve contrast and improve dehazing. Effect, deep learning dehazing Simple and effective effect

Active Publication Date: 2018-09-21
福建帝视信息科技有限公司
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the traditional method is used for image defogging, if the generation of foggy images is inconsistent with the prior conditions or assumptions of the algorithm, it will lead to a d

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 multi-scale dense connection network
  • Image defogging method based on multi-scale dense connection network
  • Image defogging method based on multi-scale dense connection network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] Such as Figure 1-8 As shown in one, the present invention discloses an image defogging method based on a multi-scale densely connected network, which is divided into the following steps:

[0059] Step 1. Training data preparation stage.

[0060] The step 1 specifically includes the following steps:

[0061] Step 1.1, select the training data set. The present invention uses the CVPR NTIRE2018 Outdoor Dehaze game data, which contains a pair of foggy and non-fog images. Among them, a foggy image is a fogless image formed by a certain algorithm.

[0062] Step 1.2, preprocess the image database to form a paired set of foggy sub-images and high-definition fog-free sub-images. Using adaptive histogram equalization method based on contrast restriction [9] Preprocess the foggy image I(x) to get the foggy image I(x) after contrast adjustment 1 ). From the foggy image I(x 1 ), press d*d (d=256 in the present invention) to take a screenshot of sub-image I c , And at the same time inter...

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 an image defogging method based on a multi-scale dense connection network. According to the method, images with different degrees of fog are reconstructed as relatively clear images, so that the quality and vision feeling of the images can be greatly improved. The invention discloses a self-adaptive histogram equalization mode for image preprocessing to increase contrast ratios of images, and a defogging effect can be remarkably improved; characteristics of different degrees of fog can be described by using a multi-scale dense connection convolutional nerve net, in addition, with effective combination of the characteristics, a most effective defogging effect can be achieved; an equation based on Retinex defogging problems is provided, so that end-to-end deep learning defogging can be carried out relatively concisely and effectively; compared with other defogging algorithms based on deep learning, the method has the effects that not only is the number of model parameters greatly reduced, but also an ideal defogging effect can be achieved under a condition of a very small amount of training data.

Description

Technical field [0001] The invention relates to the field of image enhancement, in particular to an image defogging method based on a multi-scale densely connected network. Background technique [0002] Fog is a weather phenomenon formed by the accumulation of tiny dust and water vapor particles under dry conditions. The turbid media such as fog, haze and smoke will absorb atmospheric light and cause the scattering of atmospheric light, which leads to degradation of the image of outdoor scenes collected in this weather. Usually, degraded images lose contrast and color fidelity. [0003] After passing through a certain scattering medium, the light intensity in the original direction will gradually weaken, and at the same time, due to the law of conservation of energy, the weakened light intensity will be scattered to other directions. In addition, the energy lost by scattering depends on the distance from the camera. Based on this physical phenomenon, people often use physical mo...

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
IPC IPC(8): G06T5/00G06T5/40G06N3/04G06N3/08
CPCG06N3/084G06T5/003G06T5/40G06T2207/10024G06T2207/10004G06T2207/20084G06T2207/20081G06N3/045
Inventor 刘文哲李根童同高钦泉
Owner 福建帝视信息科技有限公司
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