Video to-be-retrieved positioning method applied to video copyright protection

Abstract

The invention relates to the field of video copyright protection, and discloses a video to-be-retrieved positioning method applied to video copyright protection, which comprises the following steps: acquiring a plurality of key frame images of each video copyright data in a video copyright data set and a plurality of key frame images of to-be-retrieved video data; extracting a feature vector of the key frame image by using a deep convolutional neural network model; calculating perceptual hash values of a plurality of key frame images of the to-be-retrieved video data and perceptual hash valuesof a plurality of key frame images of each video copyright data; constructing a to-be-retrieved system added with a clustering algorithm and an inverted index; and performing quick retrieval and positioning on the to-be-retrieved video data. According to the method, the infringement fragment or the infringement picture can be accurately positioned, the identification of possible attack resistingmeans of the infringement video is enhanced, the robustness of the model is enhanced, the retrieval efficiency under mass data is improved, and the high accuracy and recall rate of video infringementretrieval are ensured.

Description

technical field [0001] The invention relates to the field of video copyright protection, in particular to a method for locating videos to be retrieved and applied to video copyright protection. Background technique [0002] With the rapid development of multimedia and Internet technology, massive video data has been widely used in various fields of society, and the problem of video copyright protection is becoming increasingly serious. Usually, video retrieval technology is used to find and compare infringing videos and original videos. It is mainly divided into two steps: how to express the feature information of the video and an efficient retrieval method. For example, the national patent publication CN111639228A discloses a "video to be retrieved method, system, device and storage medium", the invention includes receiving a video to be retrieved request, the video to be retrieved request includes the information to be retrieved; Matching is performed to obtain the video ...

AI Technical Summary

Problems solved by technology

The text-based video retrieval method of this invention mainly uses text annotation to describe the content in the video, but with the rapid growth of data volume, the cost of manual text annotation is high, which is not enough to support the huge amount of data in reality. High computational complexity under data

In addition, the existing method of using video content to search for infringement is difficult to locate the infringement from the video content when comparing the entire video, and it is also impossible to obtain the infringement of some segments or even a picture of the infringing video.

Images