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

Image super-resolution reconstruction method and device for real-time video stream

A technology for super-resolution reconstruction and real-time video streaming, which is applied in image data processing, graphic image conversion, instruments, etc. Fast reconstruction and visually pleasing effects

Pending Publication Date: 2021-05-11
北京中科深智科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the traditional SISR method takes a long time to reconstruct images, and cannot meet the requirements for real-time image super-resolution reconstruction of video streams
Most of the existing image super-resolution reconstruction methods based on deep learning have problems such as blurred reconstructed images, large amount of noise, poor visual perception, etc., and the reconstruction process is complicated, and it is also difficult to meet the real-time image super-resolution reconstruction requirements of video streams.

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
  • Image super-resolution reconstruction method and device for real-time video stream
  • Image super-resolution reconstruction method and device for real-time video stream
  • Image super-resolution reconstruction method and device for real-time video stream

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and through specific implementation methods.

[0060] Wherein, the accompanying drawings are only for illustrative purposes, showing only schematic diagrams, rather than physical drawings, and should not be construed as limitations on this patent; in order to better illustrate the embodiments of the present invention, some parts of the accompanying drawings will be omitted, Enlargement or reduction does not represent the size of the actual product; for those skilled in the art, it is understandable that certain known structures and their descriptions in the drawings may be omitted.

[0061] In the drawings of the embodiments of the present invention, the same or similar symbols correspond to the same or similar components; , "inner", "outer" and other indicated orientations or positional relationships are based on the orientations or positional ...

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 an image super-resolution reconstruction method and device for a real-time video stream, and the method comprises the steps: obtaining a video frame image, and extracting a brightness channel image, a blue channel image and a red channel image of the video frame image; taking the extracted brightness channel image of the associated video frame image as the input of an image super-resolution reconstruction model, and outputting a predicted high-resolution image of the associated video frame image by the model; and carrying out image merging on the high-resolution image associated with the video frame image and the extracted blue channel image and red channel image associated with the same video frame image, and then converting the merged image into a super-resolution image in an RGB color space. The image super-resolution reconstruction method provided by the invention is simple in principle and high in reconstruction speed, experiments show that the image super-resolution reconstruction method can be completely suitable for the image super-resolution reconstruction of the video stream, and the reconstructed super-resolution image is clear and good in visual sense.

Description

Technical field [0001] The present invention relates to the technical field of image reconstruction, and in particular to an image super-resolution reconstruction method and device for real-time video streams. Background technique [0002] Image super-resolution (SR) reconstruction aims to reconstruct a high-resolution image containing rich details by inputting one or more low-resolution images. It is important in the fields of monitoring equipment, satellite images, and medical imaging. Value. Through super-resolution reconstruction we can make single or multiple unclear images clear. [0003] At present, most research on image super-resolution reconstruction technology focuses on single-image super-resolution reconstruction (Signal Image Super Resolution, SISR), which uses the rich information contained in an image and the visual priors from sample images. , identify important visual cues to fill in image details. The traditional SISR method is based on empirical algori...

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): G06T3/40G06N3/04
CPCG06N3/04G06T3/4046G06T3/4053
Inventor 不公告发明人
Owner 北京中科深智科技有限公司
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