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

A Method of Deraining Image Based on Depth of Field and Sparse Coding

A sparse coding and image technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems affecting the imaging quality of the visual system, unfavorable image analysis, etc., and achieve good rain removal effect, scientific design, and strong practicability Effect

Active Publication Date: 2021-10-29
郑州国测智能科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When in a snowy environment, there are similar results, which greatly affects the imaging quality of the visual system, which is not conducive to subsequent image analysis

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
  • A Method of Deraining Image Based on Depth of Field and Sparse Coding
  • A Method of Deraining Image Based on Depth of Field and Sparse Coding
  • A Method of Deraining Image Based on Depth of Field and Sparse Coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The technical solutions of the present invention will be described in further detail below through specific implementation methods.

[0030] as attached figure 1 As shown, an image deraining method based on depth of field and sparse coding includes the following steps:

[0031] Step 1: Input the original image containing rain, and use joint bilateral filter and short-time Fourier transform to decompose the original image to obtain the low-frequency image I LF and high frequency image I HF , the specific methods include:

[0032] Step 1.1, performing dual-domain filtering on the original image x to obtain a guiding image g; performing bilateral filtering on the original image x and the guiding image g respectively to obtain a guiding layer image and the base layer image Take the base layer image as a low-frequency image I LF :

[0033]

[0034] in, For the obtained guide layer image, For the obtained base layer image, k(p,q) is the kernel function of bilat...

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 an image deraining method based on depth of field and sparse coding, comprising the following steps: Step 1, inputting an original image containing rain, decomposing the original image by joint bilateral filtering and short-time Fourier transform to obtain low-frequency image and high-frequency image; step 2, according to the texture characteristics of the image itself, the high-frequency image is divided into K class, each class is divided into blocks to obtain the rain-removing dictionary; step 3, the rain-removing dictionary is divided into two categories: a rain-containing dictionary and a rain-free dictionary; Rain component; step 5, using depth of field DoF value to modify the rain-free component in the high-frequency image to obtain a depth-of-field correction rain-free high-frequency map, and correcting the low-frequency image and the original image to obtain a depth-of-field correction low-frequency map; step 6 , superimpose the depth-corrected low-frequency image and the depth-corrected rain-free high-frequency image to obtain the output image after rain removal. The invention has the advantages of scientific design, strong practicability and good rain removal effect.

Description

technical field [0001] The invention relates to the technical field of image deraining, in particular to an image deraining method based on depth of field and sparse coding. Background technique [0002] With the development of contemporary technology, computer vision algorithms are often used in image analysis, detection and tracking, remote monitoring and other fields. However, affected by outdoor weather conditions such as haze, rain, snow, night, etc., image processing is greatly affected, and it is difficult to analyze and process images accurately. [0003] In all kinds of outdoor weather, the rainy environment is more complicated and the visual effect is changeable. In light rainy weather, the rain in the image will appear in the shape of raindrops, and the raindrops will distort the image background and become blurred. When the rainfall is large, there will be obvious rain streaks, and different results will be produced for different distances. When the distance is...

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): G06T5/00G06T7/42G06T7/50
CPCG06T5/003G06T2207/20024G06T2207/20048G06T7/42G06T7/50
Inventor 郧刚卢建伟郭振强侯长生陈长宝李德仁
Owner 郑州国测智能科技有限公司
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