An image super-resolution and non-uniform blur removal method based on fusion network

A super-resolution and fusion network technology, applied in image analysis, biological neural network model, image enhancement, etc., can solve problems that cannot meet the needs of practical applications, and achieve the effect of good real-time performance and high computing efficiency

Active Publication Date: 2019-02-15
XI AN JIAOTONG UNIV
View PDF19 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The representative literature of this type of method is [1,2]. However, these methods focus on processing uniform motion blur [1] or Gaussian blur [2]. When applied to more complex non-uniform motion blur scenes, the results are far from Can not meet the actual application needs

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
  • An image super-resolution and non-uniform blur removal method based on fusion network
  • An image super-resolution and non-uniform blur removal method based on fusion network
  • An image super-resolution and non-uniform blur removal method based on fusion network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention is further described below in conjunction with accompanying drawing:

[0039] A fusion network-based image super-resolution and non-uniform blur removal method, comprising the following steps:

[0040] Step 1: Preprocess the original video and obtain the image training data set: convert several segments of video collected by the high-speed motion camera into multiple pairs of spatially aligned image block triplets{l blur , l, h}, where l blur Indicates the non-uniform motion blurred image block at low resolution, which is used as the input of neural network training; l and h represent the clear image block at low resolution and the clear image block at high resolution, respectively, which are used as the true image of different branches in neural network training. value;

[0041] Step 2: Build a deep neural network: The neural network uses two branch modules to extract features for image super-resolution and non-uniform blur removal, and adaptive...

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 natural image super-resolution and non-uniform motion blur removing method based on a depth feature fusion network, which firstly realizes the restoration of a low-resolutionnon-uniform motion blur image based on a depth neural network. The network adopts two branch modules to extract features for image super-resolution and non-uniform blur removal respectively, and achieves adaptive fusion of the outputs of the two feature extraction branches through a feature fusion module that can be trained. Ultimately, the upsampling reconstruction module realizes the task of removing non-uniform motion blur and super-resolution. This method utilizes the self-generated training data set to train the network offline, thus realizing the restoration of low-resolution non-uniform motion blurred images of any input size. This method has low training difficulty, good effect and high computational efficiency, is very suitable for image restoration and enhancement of mobile devices and monitoring equipment.

Description

technical field [0001] The invention belongs to the field of computer vision and image processing, in particular to an image super-resolution and non-uniform blur removal method based on a fusion network. Background technique [0002] Image super-resolution is a class of fundamental tasks in computer vision applications. Its purpose is to restore high-resolution images from low-resolution images, improve image quality and restore image detail information. It can not only generate satisfactory high-resolution images, but also provide higher-quality image sources for deeper image processing processes such as target detection and face recognition. However, there are moving objects of different depths and motion occlusion in natural images, so non-uniform motion blur often exists in real low-resolution images, which will seriously affect the research of super-resolution algorithms. [0003] Unlike uniform motion blur images, non-uniform motion blur images are fused from adjace...

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 Applications(China)
IPC IPC(8): G06T3/40G06K9/62G06T5/00G06V10/774
CPCG06T3/4076G06T5/003G06T2207/10016G06F18/253G06F18/214G06T3/4053G06T2207/10004G06T2207/20021G06T2207/20081G06T2207/20084G06T2207/20201G06T2207/20192G06T2207/20221G06N3/08G06V10/806G06V10/803G06V10/774G06N3/045G06F18/251
Inventor 王飞张昕昳董航张康龙韦昭
Owner XI AN JIAOTONG UNIV
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