Approximate repeated video retrieval method incorporating global R features

Abstract

The invention discloses an approximate repeated video retrieval method incorporating global R features. The method comprises the steps of firstly implementing the extraction of local SIFT features of videos in a databases, based on the coordinate information of the local SIFT features, establishing a global R feature, using descriptor information of the local SIFT features to establish a BOF retrieval model, based on the BOF model, establishing a voting retrieval model, finally implementing an application information fusion strategy to fuse global geometric distribution information into the BOF model, and accurately retrieving approximate repeated video in large-scale data. The approximate repeated video retrieval method incorporating global R features fuses the global R feature can fuse the global geometric distribution information into the BOF model based on the information fusion strategy, and achieve accurate retrieval of the approximate repeated video in large-scale data.

Description

technical field [0001] The invention belongs to the technical field of video analysis and retrieval methods, and in particular relates to an approximate repeated video retrieval method fused with global R features. Background technique [0002] With the rapid development of communication technology, video capture equipment, and video editing software, the number of online videos has grown exponentially. At the same time, video-related services, such as advertising, video sharing, recommendation and monitoring, stimulate the interest of online users and participate in video-related activities, such as searching, uploading, downloading, and commenting. [0003] Today, a large number of videos are uploaded and shared on the Internet every day, and there are a large number of almost repeated videos on the Internet. The emergence of a large number of near-duplicate videos has spawned many new applications, such as: video result reordering, copyright protection, online video usag...

AI Technical Summary

Problems solved by technology

[0006] At present, most near-duplicate video retrieval methods are based on local features and BOF retrieval models, but these methods only use a single local texture information and ignore the global information of feature points, resulting in low video retrieval accuracy.

Images