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

IPTV and OTT video feature extraction method based on convolutional neural network

A convolutional neural network and video feature technology, applied in the field of IPTV and OTT video feature extraction based on convolutional neural network, can solve problems such as difficulty in video content supervision, improve storage efficiency and operating efficiency, improve efficiency and effectiveness sexual effect

Inactive Publication Date: 2021-02-09
VIXTEL TECH BEIJING CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to the huge amount of video content in IPTV and OTT services and the processing workload of video image recognition, the supervision of video content is very difficult.

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
  • IPTV and OTT video feature extraction method based on convolutional neural network
  • IPTV and OTT video feature extraction method based on convolutional neural network
  • IPTV and OTT video feature extraction method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with accompanying drawing.

[0020] The main steps of the present invention include extraction of video key frames, convolution processing of frame pictures, extraction of feature values ​​of frame pictures, and comparison of feature values ​​of frame pictures.

[0021] The extraction of video key frames can reduce a large amount of redundant information content between video frames. The extraction process of video key frames is shown in the appendix figure 1 Video key frame extraction flow chart, the process description is as follows:

[0022] 1) Suppose a video Vi contains n frames, which can be expressed as Vi={F1,...,Fn};

[0023] 2) The similarity between two adjacent frames is defined by the similarity of the color histogram;

[0024] 3) The definition of the similarity threshold between frames, the frame pictures whose similarity is lower than the threshold range can be considered as the frame...

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 belongs to the technical field of electronic information, and relates to an IPTV and OTT video feature extraction method based on a convolutional neural network. Disclosed is the IPTV and OTT video feature extraction method based on a convolutional neural network, the convolutional neural network is an important technology of image recognition, and the convolutional neural network isa neural network for replacing matrix multiplication by using convolutional calculation in a certain layer. Characteristics of the convolution operation determine that the neural network is suitablefor processing data with a network-like structure. The convolution function can extract features of the input object layer by layer. The invention provides an IPTV and OTT video feature extraction method based on a convolutional neural network by utilizing important application of the convolutional neural network in image recognition and combining video key frame picture characteristics of IPTV and OTT services, so that the efficiency and effectiveness of IPTV and OTT video feature extraction can be effectively improved, and a solid foundation is laid for IPTV and OTT video content supervisionwork. The method comprises the following steps: S1, extracting a video key frame; S2, carrying out convolution processing on frames; S3, extracting characteristic values of the frames; and S4, comparing the characteristic values of the frames.

Description

technical field [0001] The invention belongs to the technical field of electronic information, and relates to an IPTV and OTT video feature extraction method based on a convolutional neural network. Background technique [0002] In recent years, various operators have vigorously developed IPTV and OTT TV services. IPTV and OTT services have already surpassed traditional cable TV and digital TV, and the number of users has gradually expanded. Due to the characteristics of IPTV and OTT business network transmission channels, and the relevant requirements of radio and television safety broadcast management regulations, the supervision of IPTV and OTT video content is imperative for operators every month. At present, in the supervision work of IPTV and OTT video content, the first and most important link is how to obtain video content. [0003] Due to the huge amount of video content in IPTV and OTT services and the processing workload of video image recognition, the supervisio...

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): G06K9/00H04N21/234H04N21/44
CPCH04N21/23418H04N21/44008G06V20/46
Inventor 林桂云
Owner VIXTEL TECH BEIJING CO LTD
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