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

Spatio-temporal super-resolution video enhancement method and system

A super-resolution and video enhancement technology, applied in the field of image processing, to achieve the effect of reducing flow noise

Pending Publication Date: 2021-05-28
成都东方天呈智能科技有限公司
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

ST-MR in the prior art is not a method based on deep learning, and needs to input a long video to extract spatio-temporal patterns. Although Manoj et al. proposed ST-MR based on a deep network, the ST-MR method only relies on LR for interpolation. Can make full use of the advantages of ST-MR mode

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
  • Spatio-temporal super-resolution video enhancement method and system
  • Spatio-temporal super-resolution video enhancement method and system
  • Spatio-temporal super-resolution video enhancement method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0047] refer to figure 1 , is a schematic flowchart of a video enhancement method for spatiotemporal super-resolution provided by the present invention. The video enhancement method of the spatio-temporal super-resolution comprises the following steps:

[0048] Step S1, collecting a video data set, performing video data enhancement processing on the video data set, and then converting the video data set into a file in a predetermined format and reading the data, s...

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 present invention provides a spatio-temporal super-resolution video enhancement method and system that reduces flow noise caused by large motion through flow refinement loss, and utilizes a temporal and spatial correlation, spatio-temporal joint learning, direct connection from a low resolution LR to a high resolution HR in a multi-resolution ST-MR, and a multi-resolution ST-MR, direct connection from a low resolution LR to a high resolution HR. Spatio-temporal S-SR and the temporal resolution T-SR are enhanced by obtaining rich multi-scale features, and finally, a space-time super-resolution network STAMnet is formed, so that the problem that ST-MR only independently processes context information in time and space is solved, the frame rate is improved through video interpolation, the spatial resolution of a video frame is improved, and the resolution ratio of the video frame is improved. The context information is extracted from the spatio-temporal super-resolution video, so that the accuracy and definition of the video can be improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a video enhancement method and system for spatio-temporal super-resolution. Background technique [0002] Spatio-temporal super-resolution ST-MR converts low-spatial-resolution video into spatio-temporal high-resolution video, while traditional ST-MR only processes contextual information in time or space alone. Spatial resolution S-SR of multiple input frames, that is, multi-image and video SR by spatially aligning similar frames, then parsing spatial low-resolution S-LR to spatial high-resolution S-HR, and temporal resolution T-SR The intermediate frames are constructed by video interpolation, thus improving temporal low-resolution T-LR to temporal high-resolution T-HR. ST-MR in the prior art is not a method based on deep learning, and needs to input a long video to extract spatio-temporal patterns. Although Manoj et al. proposed ST-MR based on a deep network, the ST-M...

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): G06T3/40G06T5/00
CPCG06T3/4007G06T3/4053G06T5/70
Inventor 闫超卢丽韩强
Owner 成都东方天呈智能科技有限公司
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