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

Single-image-oriented rain removal method based on cascaded hole convolutional neural network

A technology of convolutional neural network and single image, which is applied in the direction of biological neural network model, neural architecture, image enhancement, etc., to achieve the effect of generalization and integrity assurance

Active Publication Date: 2019-11-26
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a single image-oriented rain removal method based on cascaded hole convolution neural network, which is used to solve the restoration problem of a single image taken in a rainy day

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
  • Single-image-oriented rain removal method based on cascaded hole convolutional neural network
  • Single-image-oriented rain removal method based on cascaded hole convolutional neural network
  • Single-image-oriented rain removal method based on cascaded hole convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] This embodiment provides a method for removing rain from a single image based on a cascaded hole convolutional neural network, including the following steps:

[0036] Step 1: Construct a deraining model based on cascaded dilated convolutional neural network:

[0037] Step 1-1: Modeling the rainwater part of the rainwater image according to the model features of the rainwater image;

[0038] The image rain model widely used in academia and industry is: O=B+R. In this rain model, O is an image containing rain, B is a background layer, and R is a rain layer; but there are some shortcomings in this rain model, which will When the rain-free image is synthesized with the rain image, the overlay method of the background layer plus the rain layer is directly used. When using this model to separate the background of the rain image synthesized by the rain model, it is necessary to use the rain removal method of the model to extract the rain image. The features are identified at ...

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 belongs to the technical field of image rain removal, and provides a single-image-oriented rain removal method based on a cascaded hole convolutional neural network, which is used for solving the problem of restoration of a single image shot in rainy days. The method comprises the following steps: firstly, modeling rainwater, and dividing a rain image into a rainwater region layer, arainwater layer and a background layer; extracting a rainwater region layer image from an input image through cascaded multi-channel convolutional neural networks with different void ratios, obtaining a rainwater layer image through convolution, and obtaining a rain-removed background layer image through convolution and summation of the input image. Details of different scales of the image are effectively extracted through the cascaded hole convolutional neural network, the network adopts a residual network structure to increase the network depth, and the over-fitting problem is avoided; an evaluation experiment is carried out on a public data set, and the experiment shows that compared with a single-image rain removal classic method, the peak signal-to-noise ratio (PSNR) can be improvedby 2-8, and the image structural similarity (SSIM) can be improved by 0.04-0.22.

Description

technical field [0001] The invention belongs to the technical field of image deraining, and relates to the application of deep learning in image deraining, in particular to a method for deraining a single image based on a cascaded hollow convolutional neural network. Background technique [0002] Most outdoor vision systems, such as surveillance and autonomous navigation, require accurate feature detection on outdoor scene images for the next step of system processing. In severe weather, usually such as heavy rain, the content and color of the image often change drastically and have a large difference from the original image; this rainy image will cause the loss of global image contrast and color effects, resulting in many images Details are lost. For a computer vision system that relies heavily on the quality of the input image, the result may be disastrous. For example, for the vision system of autonomous driving, the input image in rainy days is likely to cause the targe...

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): G06T5/00G06N3/04
CPCG06N3/045G06T5/77
Inventor 张萍彭一凡卢韶强申奉璨蒲恬
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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