Copy video detection method based on continuous copy frame sequence

Abstract

The invention discloses a copy video detection method based on a continuous copy frame sequence, which arms at providing a method of effectively detecting a splicing condition of copy and non copy fragments of a to-be-detected video. In the technical scheme, key frames and key frame features of a reference video and a to-be-detected video are extracted firstly to obtain a reference video key framefeature matrix and a to-be-detected video key frame feature matrix; row vectors with the minimum Euclidean distances are searched in the reference video key frame feature matrix for each row in the to-be-detected video key frame feature matrix to obtain the most similar reference video key frame sequence number list R<*> and the most similar reference distances d1, d2,...,di,...,dM; and based onthe R<*> and d1, d2,...,di,...,dM, whether the to-be-detected video key frame is a copy frame is judged, whether the to-be-detected video is a copy video is judged, and the copy fragment in the copy video is positioned. By adopting the method in the invention, the condition in which the to-be-detected video is spliced by a copy fragment and a non-copy fragment can be effectively solved, and the similar key frame matching speed and the accuracy are improved.

Description

technical field [0001] The invention relates to a method for detecting copied video in the technical field of multimedia information processing, and is a video detection method capable of adapting to various editing transformations. Background technique [0002] With the rapid development of network technology, video hardware processing technology and software processing technology, video data shows a trend of massive growth in many fields. At the same time, the rapid increase of Internet users and the generalization of video technology, social media platform video sharing and other factors make the downloading, re-editing and re-uploading of video data more convenient and fast, and the number and types of videos on the Internet are growing explosively . Taking the YouTube video site as an example, more than 100 hours of video are downloaded every minute. On some social networking sites, a large number of videos are also downloaded and shared every day, which leads to a lar...

AI Technical Summary

Problems solved by technology

The method based on frame fusion can cope with video frame rate changes, frame insertion, frame loss and other editing transformations, and can also solve the situation where there are only part of the copied clips in the video, but the method based on frame fusion is complex to calculate and difficult to implement.

[0006] Therefore, this series of research faces some typical limitations in copy video detection: First, most of the current research uses local features with high robustness for similarity matching of key frames, resulting in the speed of similarity matching of key frames is still relatively low. slow

There are two main reasons affecting the speed: (1) the number of key frames in the video library is huge, and it is a time-consuming task to perform key frame similarity matching in the entire library; (2) the number of local key points in the key frames is huge, The key point description vector has a high dimensionality, and it takes a lot of time to perform one-to-one matching of local key points between key frames

Second, most of the current copy video detection research focuses on the case where the video to be detected is equal to the length of the reference video and the video to be detected is a subset of the reference video. In these two cases, the video to be detected is a pure copy, and there is no non-copy segment

Although these methods have achieved relatively good results in solving their respective application problems, the application area is too narrow and the applicability is not high. When the subset in the current research method cannot be solved, the accuracy of detection will be greatly reduced

[0007] Therefore, the research status of copy video detection cannot effectively meet the needs of video retrieval, copyright protection, and video content supervision. It is particularly important to propose a fast and effective copy video detection method.

Images