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

A short video copyright detection method and system

A detection method and detection system technology, which is applied in the field of short video processing, can solve problems such as not being able to obtain good results, not being able to capture information on time series well, and color histograms not being able to be accurately distinguished, so as to reduce data redundancy. The effect of reducing the amount of data processing and quick recall

Active Publication Date: 2021-10-19
HANGZHOU QUWEI SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 3D convolutional network (C3D network): Convolutional neural network has been widely used in machine vision in recent years. 2D convolution can extract features from pictures, but it cannot capture temporal information well. Therefore, direct video feature extraction does not achieve very good results, so 3D convolutional networks are proposed to solve this problem
For example, the background subjects of different football short videos are all green stadium grass, and the color histogram cannot be accurately distinguished

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 short video copyright detection method and system
  • A short video copyright detection method and system
  • A short video copyright detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] like figure 1 As shown, this embodiment proposes a short video copyright detection method, including:

[0066] S1. Obtain a short video with copyright, and generate a picture frame vector corresponding to the short video with copyright;

[0067] The invention compares the short video to be detected with the short video with copyright, so as to detect the copyright of the short video to be detected. Therefore, the present invention first constructs sample data. In order to realize the copyright detection of the short video, the present invention generates a corresponding vector for the short video, so as to perform copyright detection of the short video based on the vector. In the existing short video vector construction process, it is usually necessary to segment short videos and calculate keyword weights. For short videos with little text information, it is difficult to construct short video vectors based on text information, and the processing efficiency of word seg...

Embodiment 2

[0093] like Figure 5 As shown, this embodiment proposes a short video copyright detection system, including:

[0094] The first processing module is used to obtain the short video with copyright, and generate the picture frame vector corresponding to the short video with copyright;

[0095] The invention compares the short video to be detected with the short video with copyright, so as to detect the copyright of the short video to be detected. Therefore, the present invention first constructs sample data. In order to realize the copyright detection of the short video, the present invention generates a corresponding vector for the short video, so as to perform copyright detection of the short video based on the vector. In the existing short video vector construction process, it is usually necessary to segment short videos and calculate keyword weights. For short videos with little text information, it is difficult to construct short video vectors based on text information, a...

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 short video copyright detection method and system. The detection method includes: S1, acquiring a copyrighted short video, and generating a picture frame vector corresponding to the copyrighted short video; S2, converting the copyrighted short video The corresponding picture frame vector of the short video is stored in Faiss; S3, generate the corresponding picture frame vector for the short video to be detected, and utilize the corresponding picture frame vector of the short video to be detected to index Faiss; S4, return and the Detect the candidate short video corresponding to the picture frame vector distance corresponding to the short video less than the first threshold; S5, calculate the number of consecutive similar picture frames between the short video to be detected and each candidate short video; S6, based on the similarity The number of picture frames determines whether the short video to be detected violates the copyright of the corresponding candidate short video. The present invention can comprehensively acquire the temporal and spatial dimension features, global features and local features of the short video.

Description

technical field [0001] The invention relates to the technical field of short video processing, in particular to a short video copyright detection method and system. Background technique [0002] Short videos are gradually replacing text, pictures, and music, becoming the mainstream way of media communication. Short videos have the characteristics of fast output, wide influence and large number of participants. In order to protect the rights and interests of original users and avoid copyright disputes, short video copyright detection has become an essential capability for every short video platform. There are usually two methods of copyright detection in the video field: video watermark and short video content. Difficulties in copyright detection in the video field include: video format conversion, video cutting, video fragment splicing, video size cropping, adding special effects, adding watermarks, etc. [0003] Most of the existing Content-Based Copyright Detection (CBCD...

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): H04N21/8355
CPCH04N21/8355
Inventor 范俊顾湘余刘昱龙李文杰黄睿智
Owner HANGZHOU QUWEI SCI & TECH
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