Video key frame extraction method based on multi-characteristic fusion shot clustering

Abstract

The invention discloses a video key frame extraction method based on multi-characteristic fusion shot clustering and belongs to the video content analysis field. Research of the method is based on video shot segmentation. The method comprises the following steps of step1, extracting a group of image frame set in a video shot, extracting an HSV histogram characteristic of each frame of image and a canny edge contour characteristic, and weighting and forming characteristic information of key frame clustering; step2, using an adaptive mean value clustering method to successively classify each frame of image to a corresponding clustering cluster and updating a clustering center of each clustering cluster in real time; step3, extracting an image frame which is nearest to each clustering center as a key frame of each cluster respectively, and arranging according to a time sequence so as to form a key frame set; and step4, calculating an attention index of each key frame and extracting one frame with a highest attention index as a representative frame of a video. By using the method of the invention, problems that flexibility of a traditional key frame extraction algorithm is not high and a fidelity is low are solved.

Description

technical field [0001] The invention belongs to the field of video content analysis, and in particular relates to a video key frame extraction method based on multi-feature fusion shot clustering. Background technique [0002] With the development of computer, communication and multimedia technology, the data volume of multimedia video data is growing in a blowout style. At the same time, traditional video analysis methods cannot adapt to the continuous growth of data volume and the increasingly complex structure of video data. In the structured analysis of video data, it is first necessary to decompose the complete video segment into different shot units. However, a shot still contains a lot of data content, and the inter-frame redundancy within the shot is still relatively large. The calculation amount and calculation repetition rate of directly analyzing the video shot unit will still be relatively high. Extract representative keyframe sequences from content information....

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a method for extracting key frames based on multi-feature fusion shot clustering for the common problems existing in current video key frame extraction

This method solves the problem that the number of extracted key frames is limited by the initial conditions and the distribution of key frames is uneven in the existing methods, and improves the extraction effect of the algorithm for different types of video data, with high universality

Images