Video restoration method

A repair method and video technology, applied in neural learning methods, image enhancement, image analysis, etc., to achieve semantically correct, efficient prediction and repair optimization, and reduce computing time.

Active Publication Date: 2020-05-05
PEKING UNIV
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This kind of video restoration method mainly fully combines the three technologies of image segmentation, image restoratio

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
  • Video restoration method
  • Video restoration method
  • Video restoration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030]In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further elaborated below through specific embodiments and accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0031] The present invention mainly considers that the traditional video repair based on block matching mainly focuses on the search and matching of spatial pixel blocks, and is suitable for fast filling of content blocks in large-area missing areas, but it lacks the consideration of time dimension information, especially in complex scenes. Not considering the context information of the preceding and following frames will lead to unsatisfactory inpainting effect. The learning-based deep neural network repair method can deal with the approximation, prediction and generation of a sequence of high-quality pixels in t...

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 provides a video restoration method, and belongs to the field of communication and information systems. The method mainly comprises the following steps of: extracting motion informationin an image frame sequence based on a mask corresponding to an original video containing a missing area; arranging a cubic sliding block for traversing and sliding in three dimension directions of theframe width, the frame height and the frame number of the original video; when the cubic sliding block slides to a mark region, randomly initializing a larger cubic sliding space; comparing the motion information with the optical flow characteristic information of the edge of the mask region, finding the most matched sample block in the sliding space range, filling and reconstructing the pixel characteristics of the mask region, continuing to traverse until all mask regions in the original video are restored, inputting the restored mask regions into a forward-backward neural network for optimization, and outputting a restored complete video. According to the method, a high-quality video restoration effect is achieved at the minimum calculation cost.

Description

technical field [0001] The invention belongs to the field of communication and information systems, and in particular relates to a novel video restoration method combined with 3D image block filling and deep neural network optimization. Background technique [0002] Video is an important carrier of multimedia information dissemination and an important source for human beings to obtain external information. With the rapid development of the Internet and digital technology, digital video has been widely used due to its advantages of easy storage and convenient transmission. However, due to channel noise and other reasons during the transmission of digital video sequences in low signal-to-noise ratio channels, it is easy to cause some image frames in the video to lose part of the information, causing problems such as scratches, spots, and flickering in the video sequence frames, thereby destroying the quality of the video. Completeness and readability affect the accuracy of in...

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): G06T5/20G06T7/11G06T7/246G06T5/00G06N3/08
CPCG06N3/08G06T5/002G06T5/003G06T5/20G06T2207/10016G06T7/11G06T7/246
Inventor 黄燕杨川川
Owner PEKING 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