Video copy detection method based on multimodal features and tensor decomposition

Abstract

The invention provides a video copy extraction method based on tensor decomposition, in particular to a video copy detection method based on multimodal features and tensor decomposition, which includes the following steps: (1) video preprocessing: video clips are standardized by spatial-temporal sampling; (2) video tensor modeling and tensor decomposition: the global, local and time domain features of the video are respectively extracted, tensor modeling is carried out, and the Tucker model is utilized to carry out tensor decomposition, so that a nuclear tensor and a low-order tensor are obtained; (3) video fingerprint matching: the nuclear tensor is utilized to carry out rough matching, and a video fingerprint is utilized to carry out fine matching in a coarse selection. Compared with the prior art, the method realizes the true complementary fusion of multimodal features of a video, not only overcomes the defect of poor robustness of video fingerprints constructed with single-mode features, but also realizes the temporal associated co-occurrence between a variety of modes of features, and increases the accuracy and efficiency of video copy extraction.

Description

technical field [0001] The invention relates to a video copy detection method, in particular to a video copy detection method based on multi-mode features and tensor decomposition, and belongs to the technical field of video and multimedia signal processing. Background technique [0002] Digital video has gradually become the primary form of multimedia for users because of its intuition, specificity and vividness. With the development of network technology and the continuous improvement of network bandwidth, video transmission and storage have become more and more convenient. Therefore, there are more and more Internet video sites, and video content is becoming more and more abundant. The problem of network information security has also become increasingly prominent. Network users can download, edit and upload videos at will, so there are a large number of repeated videos in the network, which greatly affects the efficiency of video retrieval. At the same time, due to the ...

AI Technical Summary

Problems solved by technology

Therefore, in the case of personal video production and network communication becoming more and more popular, content-based video copy detection technology has important theoretical value and application value, and has become a research hotspot in the field of multimedia information processing in recent years. Detection techniques can be divided into different types from different angles, but in general, they can be divided into two categories. One is based on global features, such as color histograms, block grayscale order metrics, etc., based on frequency The domain method also belongs to this category. The advantages of this type of method are fast speed and small amount of calculation. The disadvantage is that some local attacks and post-processing attacks on the video (such as adding video subtitles, partial cutting, etc.) are not effective; The second type is a method based on local features, mainly frame local feature point descriptors, such as Harris feature points, SIFT (Scale Invariant Feature Transform) and SURF (Speed-up Robust Feature), such methods have a good effect on local video attacks Robustness, but sometimes the complexity of the algorithm is higher

Images