A time-domain detection method of video transmission quality based on deep learning frequency identification

A technology of video transmission and deep learning, applied in the field of video transmission quality time domain detection based on deep learning frequency identification, can solve problems such as difficulty in calculating picture freezing time and picture delay time, and inability to fully reflect picture freezing and picture delay performance.

Active Publication Date: 2021-09-03
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The former cannot fully reflect the picture freezing and picture delay performance of video transmission in the time domain; while the latter is difficult to calculate the picture freezing time and picture delay time

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
  • A time-domain detection method of video transmission quality based on deep learning frequency identification
  • A time-domain detection method of video transmission quality based on deep learning frequency identification
  • A time-domain detection method of video transmission quality based on deep learning frequency identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] In order to make the objectives, technical solutions, and advantages of the present invention, the present invention will be described in more detail below with reference to the embodiments and drawings.

[0014] like figure 1 As shown, a video transmission quality time domain detection method process based on depth learning frequency standard, including the following steps:

[0015] Step 10 Production to detect a video of the video transmission time domain indicator, calibrate each video frame serial number N in the video specific location s With the check number N c As a video label, referred to as the frequency standard;

[0016] Step 20 Train the SSD target detection network to detect the video frame as an input of the SSD target, used to detect the targets in the frequency standard. Target box J = 1, 2, 3, ..., n, n is the total number of targets;

[0017] Step 30 From the detected and Extraction and Used to locate video frames, Is it incorrect to check if the...

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 a time-domain detection method of video transmission quality based on deep learning frequency identification. The method includes: making a video for detecting time-domain indicators of video transmission, and marking the serial number and verification of each video frame at a specific position of the video. number, as a video label, referred to as a frequency standard; train the SSD target detection network, and use the video frame as the input of the SSD target detection network to detect each target and target frame in the frequency standard; extract from the detected target and target frame Serial number and verification number, the serial number is used to locate the video frame, and the verification number is used to verify whether the identification of the frequency standard is wrong; in one detection, the video frames of the sending end and the receiving end of the video transmission are extracted at the same time, and input into the SSD respectively In the target detection network, extract the respective frequency standards, judge whether there is a picture freeze, calculate the picture freeze time, and calculate the picture delay.

Description

Technical field [0001] The present invention relates to the field of target detection, and more particularly to a video transmission quality time domain detection method based on depth learning frequency standard. Background technique [0002] Video is generated due to network conditions, channel quality, and cache, etc. during transmission, the screen freeze can affect the experience of users watching the video, and in a particular scene such as real-time video call, the screen delay is also required. Try to avoid, so as far as the screen is frozen in video transmission, the time domain detection of the picture delay is very important. The existing video transmission quality detection is based on the image quality to evaluate video transmission quality, and the technical research in video transmission quality time domain detection is more concentrated in packet loss, loss of frame and image distortion, and utilizing time domain images The context judging the screen freezes. The ...

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 Patents(China)
IPC IPC(8): H04N17/00G06T7/00
CPCG06T7/0002G06T2207/10016G06T2207/30168H04N17/00H04N17/004
Inventor 刘桂雄蒋晨杰
Owner SOUTH CHINA UNIV OF TECH
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