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

A video image real-time deblurring method based on a neural network

A neural network and video image technology, applied in the field of image processing, can solve the problems of blurred images, slow processing speed, poor recovery effect, etc., achieve good deblurring effect, improve training speed, and improve deblurring speed

Active Publication Date: 2019-02-19
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF5 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention is to overcome the defects of the existing video deblurring algorithm that the processing speed is too slow or the recovery effect is poor, and to solve the image blurring problem caused by relative motion between the camera and the shooting object in real time, and proposes a method based on neural network The video image deblurring method, which has the advantages of fast processing speed and good recovery effect

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 video image real-time deblurring method based on a neural network
  • A video image real-time deblurring method based on a neural network
  • A video image real-time deblurring method based on a neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The implementation of the method of the present invention will be further described in detail below in conjunction with the accompanying drawings and in conjunction with specific implementations.

[0029] A neural network-based video image deblurring method of the present invention aims to solve the image blurring problem caused by relative motion between a camera and a shooting scene in real time by using a video sequence with the help of a neural network. The specific process is:

[0030] 1. Build a neural network:

[0031] Such as figure 1 As shown, this example builds an end-to-end neural network, which is mainly composed of an encoder, a dynamic fusion network, and a decoder. The specific implementation of each part is as follows:

[0032] (1) Encoder: such as figure 2 As shown in a, it consists of two convolutional layers, cascaded layers and four single-layer residual structures. The convolution kernel size of the first convolutional layer is 5×5, and the ste...

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 video image deblurring method based on a neural network, which comprises the following steps: constructing a neural network composed of an encoder, a dynamic fusion network and a decoder; The encoder consists of two layers of convolution, cascaded layers and four single-layer residual structures stacked in turn. The dynamic fusion network is used to weigh and fuse the feature map saved in the last deblurring stage with the feature map obtained by the current stage encoder. The decoder comprises four single-layer residual structures, wherein the four single-layer residual structures are connected with two branches; The final output image of the neural network is the image obtained by adding the intermediate frame image of the input image sequence and the output image of the first branch of the decoder. The loss function is constructed and the neural network is trained. The trained neural network is used to de-blur the video image. The method of the invention has the advantages of fast processing speed and good recovery effect.

Description

technical field [0001] The invention relates to a neural network-based real-time deblurring method for video images, which belongs to the technical field of image processing. Background technique [0002] In the information age, portable imaging devices have been widely used in fields such as video surveillance, visual navigation, automatic license plate recognition, remote sensing, medical treatment, and space exploration. The relative motion between the camera and the shooting object and the inappropriate distance between the shooting object and the optical center of the camera will cause motion blur and defocus blur during the exposure of the imaging device. Due to the lack of detailed information in the image, blurred images cause a lot of inconvenience to some applications that require extremely high details. Therefore, recovering clear and detailed images from blurred images has very important application value. [0003] The current image deblurring algorithms are us...

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
CPCG06T2207/10016G06N3/045G06T5/73
Inventor 陈靖金国敬黄宁生
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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