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

Single image rain removal method based on composite residual network and deep supervision

A single image, residual technology, applied in the field of image processing, can solve the problem of ineffective full convolution network

Active Publication Date: 2020-04-24
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in their work Fu et al. point out that ordinary fully convolutional networks (FCNs) are ineffective in learning direct mapping

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 rain removal method based on composite residual network and deep supervision
  • Single image rain removal method based on composite residual network and deep supervision
  • Single image rain removal method based on composite residual network and deep supervision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0042] A Single Image Deraining Method Based on Composite Residual Network and Deep Supervision:

[0043] 1. When constructing the training set, images with rain in multiple directions and corresponding clean images in natural scenes can be collected. Currently, there is a public data set RainH containing multiple rain line directions, which can be used directly set to train the network. In addition, according to the scenes you need, such as automatic driving, vehicle detection, etc., you can collect clean images of related scenes, and then use some existing rain line synthesis methods to synthesize corresponding data sets;

[0044] 2. When preprocessing the input, first randomly select images from the training set, but instead of directly putting the images into the ne...

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 a single image rain removal method based on a composite residual network and deep supervision, and the method comprises the following steps: constructing a training set, and collecting images with rain in a plurality of directions in a natural scene and corresponding clean images; preprocessing: randomly selecting an image pair from the training set as the input of the network; extracting features, and inputting the image blocks with rain into a composite residual error network containing a plurality of residual error modules for processing to obtain multi-level features; performing image reconstruction: splicing the output features of each residual module, inputting the spliced output features into a convolution layer to obtain a three-channel image, and taking thethree-channel image as a final restored image; and supervising the output of each residual error module by using the clean image, i.e., deeply supervising, so as to optimize network parameters. According to the method, the rain strips in multiple directions are effectively removed, scene detail information can be well reserved, and the method can be applied to various image restoration applications.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for removing rain from a single image based on a composite residual network and deep supervision. Background technique [0002] When shooting in rainy days, some linear white spots will be formed on the captured image. Therefore, the purpose of image removal task is to remove the rain lines on the captured image, so as to restore the damaged background in the image. [0003] In recent years, computer vision based on digital image processing has been widely used in scientific research, social production and people's daily life, such as in remote monitoring, intelligent transportation, remote sensing, medicine, military defense and other fields. However, in rainy conditions, the captured images and videos are susceptible to the scattering and blurring of raindrops, which makes the image blurred and the visibility decreases, which greatly limits the performance of outdoor vi...

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): G06T5/00
CPCG06T2207/20081G06T2207/20084G06T5/73Y02A90/10
Inventor 许勇彭嘉怡李芃
Owner SOUTH CHINA UNIV OF 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