Method for high-speed self-adaptive video keyframe extraction

Abstract

The invention discloses a method for high-speed self-adaptive video keyframe extraction. The method comprises: 1) for each to-be-processed video file, resolving the video file to extract data frames whose type is KEY_FRAME; 2) according to actual requirements, selecting an extracted data frame whose type is KEY_FRAME, using the data frame as the first keyframe of the video file, and storing the data frame in a keyframe database; and then, calculating similarity of a subsequently extracted data frame whose type is KEY_FRAME and a previous keyframe of the video file in the keyframe database, if the similarity is smaller than or equal to a given threshold value, using the data frame in the type of KEY_FRAME as the keyframe of the video file, and storing the data frame in the keyframe database; if not, giving up the extracted data frame in the type of KEY_FRAME. The method greatly improves extraction speed of keyframes.

Description

technical field [0001] The invention belongs to the field of intelligent video analysis, in particular to a key frame extraction method of high-speed self-adaptive video. Background technique [0002] With the development of multimedia data technology, video data in multimedia data has gradually become one of the most important components of multimedia data, which can more realistically record more details in terms of time and space. However, while the multimedia data information in the network brings convenience to people, it also brings many negative effects. The widespread dissemination of some videos containing bad information (such as violence, terror, vulgarity, etc.) on the Internet seriously threatens network security and endangers the safety of Internet users. In order to ensure the health of the network environment, it is necessary to quickly and accurately analyze and process bad videos from massive video data. Therefore, bad video detection in intelligent video...

AI Technical Summary

Problems solved by technology

For the slow problem of the existing key frame method, the present invention accurately locates the KEY_FRAME data frame in the video compression data stream (this variable is defined in the video decoding open source program, and this type of video frame can be processed without referring to other video frames. decoding), instead of decoding all video sequences and then performing key frame extraction operations, thus greatly improving the key frame extraction speed

In addition, in order to solve the problems of poor representativeness of key frames extracted by previous algorithms and poor adaptability caused by a fixed number of key frames, the present invention first determines the normalized threshold between adjacent key frames through manually labeled experimental data, and then the threshold Applied to the extraction algorithm to adaptively adjust the number of key frames to obtain representative key frames in the video sequence

Images