Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Adaptive coding method and system based on deep learning, equipment and medium

An adaptive encoding and deep learning technology, applied in the fields of adaptive encoding methods and systems, equipment, and media, can solve problems such as undeployment and inability to make full use of decoding chips, and achieve the effects of improving performance, reducing bandwidth consumption, and improving performance

Inactive Publication Date: 2020-12-01
杭州皮克皮克科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing video coding standards (h264, h265, etc.) have been widely used in the industry, and there are a large number of corresponding decoding chips. If deep learning technology is introduced, the existing decoding chips cannot be fully utilized and cannot be implemented. Wide and effective deployment

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
  • Adaptive coding method and system based on deep learning, equipment and medium
  • Adaptive coding method and system based on deep learning, equipment and medium
  • Adaptive coding method and system based on deep learning, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The embodiments of the present invention are described in detail below. This embodiment is implemented on the premise of the technical solution of the present invention, and detailed implementation methods and specific operating procedures are provided, but the protection scope of the present invention is not limited to the following implementation example.

[0047] Such as figure 1 Shown is a flowchart of an adaptive encoding method based on deep learning according to an embodiment of the present invention.

[0048] Please refer to figure 1 , the adaptive coding method of this embodiment includes the following steps:

[0049] S11: Input the video, perform adaptive downsampling based on deep learning for each frame in the input video, adaptively select the resolution of each frame, and obtain the downsampled image;

[0050] S12: Encode the down-sampled image obtained in S11, and then compress it to the decoding end;

[0051] S13: Decoding at the decoding end;

[00...

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 adaptive coding method and system based on deep learning, equipment and a medium, and the method comprises the steps: inputting a video, carrying out the adaptive downsampling based on deep learning of each frame in the input video, and obtaining a downsampled image; encoding the down-sampled image, and then compressing the down-sampled image to a decoding end; carryingout decoding at a decoding end; and performing video up-sampling on the decoded video to obtain a reconstructed video. The system comprises an adaptive downsampling module based on deep learning, which is used for carrying out adaptive downsampling based on deep learning on an input video to obtain a downsampled image; an encoding module which is used for encoding the down-sampled image and then compressing the down-sampled image to a decoding end; a decoding module which is used for decoding; and a reconstructed video module which is used for performing video up-sampling on the decoded videoto obtain a reconstructed video. According to the method, the resolution is changed based on deep learning, so that the performance is improved, and the method is compatible with the existing coding standard.

Description

technical field [0001] The present invention relates to the technical field of video coding, in particular to a deep learning-based adaptive coding method, system, device, and medium. Background technique [0002] Existing video or image coding algorithms based on deep learning are difficult to deploy in practical applications because they are not compatible with existing standards. [0003] Existing video coding methods based on deep learning generally need to embed deep learning technology in the encoder part to replace some existing modules (such as mode selection or performance enhancement or super-resolution or end-to-end training). Therefore, the decoder needs to be modified accordingly, that is, the decoder needs to be embedded with the corresponding deep neural network. However, the existing video coding standards (h264, h265, etc.) have been widely used in the industry, and there are a large number of corresponding decoding chips. If deep learning technology is int...

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): H04N19/132H04N19/85
CPCH04N19/132H04N19/85
Inventor 鲁国王培其他发明人请求不公开姓名
Owner 杭州皮克皮克科技有限公司
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
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