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

Distributed embedded real-time video stream processing system and method based on deep learning

A technology of real-time video streaming and deep learning, applied in the field of video processing, can solve problems such as the inability to process continuous video data quickly, achieve real-time effects, improve processing efficiency, and reduce power consumption

Inactive Publication Date: 2017-08-18
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF4 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above problems, the present invention overcomes the inability of embedded devices in the prior art to quickly process continuous video data, and the problems in bandwidth, delay and availability when processing high-flow and real-time streaming data, and provides a deep learning-based Distributed embedded real-time video stream processing system and method, the system and method greatly improve the efficiency of video stream processing and reduce the power consumption of embedded devices

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
  • Distributed embedded real-time video stream processing system and method based on deep learning
  • Distributed embedded real-time video stream processing system and method based on deep learning
  • Distributed embedded real-time video stream processing system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] As introduced in the background technology, there are embedded devices in the prior art that cannot process continuous video data quickly, as well as problems in bandwidth, delay and availability when processing high-traffic and real-time streaming data, providing a deep learning-based A distributed embedded real-time video stream processing system and method, the system and method greatly improve the efficiency of video stream processing and reduce the power consumption of embedded devices.

[0062] In order to achieve the above purpose, this embodiment adopts the following technical solution:

[0063] A distributed embedded real-time video stream processing system based on deep learning, such as figure 1 As shown, the system includes:

[0064] A video data acquisition layer, the video data acquisition layer collects video data and performs preprocessing;

[0065] and

[0066] Video data processing layer, described video data processing layer comprises embedded GPU ...

Embodiment 2

[0082] As introduced in the background technology, there are embedded devices in the prior art that cannot process continuous video data quickly, as well as problems in bandwidth, delay and availability when processing high-traffic and real-time streaming data, providing a deep learning-based A distributed embedded real-time video stream processing system and method, the system and method greatly improve the efficiency of video stream processing and reduce the power consumption of embedded devices.

[0083] In order to achieve the above purpose, this embodiment adopts another technical solution as follows:

[0084] A distributed embedded real-time video stream processing method based on deep learning, such as figure 2 As shown, the method is based on a deep learning-based distributed embedded real-time video stream processing system of the above-mentioned embodiment, and the specific steps of the method include:

[0085] (S1) Video data collection: the video data collection ...

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 relates to a distributed embedded real-time video stream processing system and method based on deep learning. A video data acquisition layer collects video data and carries out pretreatment through an ARM board; a video processing layer uses a deep learning algorithm to perform video processing on an embedded GPU processor cluster according to a specified video processing task; a GPU resource scheduling layer monitors GPU use conditions in the embedded GPU processor cluster in real time and carries out scheduling according to a scheduling policy; a storage layer uploads the processing result to a cloud storage server; and a service layer feeds back the result to a client in a visual manner. The distributed embedded real-time video stream processing framework based on deep learning combines video processing and deep learning, and realizes parallelization of video processing by utilizing distributed embedded technology to reach a real-time video processing effect; and by applying deep learning to the video processing, video processing accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of video processing, and in particular relates to a distributed embedded real-time video stream processing system and method based on deep learning. Background technique [0002] At present, with the continuous improvement of semiconductor technology and chip design level, the performance of electronic equipment has been greatly improved; among them, especially embedded application terminals have achieved unprecedented development. Embedded application terminals in the prior art can handle a larger amount of data and cover a wider range of fields. Some applications that can only be implemented on PCs have also appeared in embedded devices, such as video processing. On the other hand, people's higher requirements for the application of embedded devices are also promoting the rapid development of embedded application terminals, such as requirements in video processing and other aspects. Originally, the applic...

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): G06T1/20G06N3/08H04L29/08
CPCH04L67/1097G06N3/08G06T1/20
Inventor 张卫山孙浩云赵德海徐亮卢清华李忠伟宫文娟
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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