A Method for Obtaining Video Summarization Based on Manifold Sorting

Abstract

The invention relates to video processing and classifying, and provided a method for calculating the similarity among data from global features of the data by utilizing an internal manifold structure among the data and constructing video abstraction on the basis of a manifold sorting algorithm. According to the technical scheme, the video abstraction method based on manifold sorting comprises the steps that visual features of video frames are extracted, and the video frames are regarded as points in a space; data points are sorted by means of the manifold sorting algorithm, wherein manifold sorting is described as the following process that a network with weight is constructed according to data, a positive sorting fraction is allocated to a point related to query, a zero sorting fraction is allocated to remaining to-be-sorted points, all the points transmit the fractions to the points near the points through the weight network, the propagation process is repeatedly conducted until the overall network reaches a stable state, and all the points obtain the final sorting scores at the moment. The method is mainly applied to video process and classifying scenes.

Description

technical field [0001] The present invention relates to video processing and classification, specifically, to a video summarization method based on manifold sorting. Background technique [0002] With the rapid development of information technology, a large number of multimedia data such as images and videos have emerged, which has become one of the important ways for people to obtain information. However, due to the sharp increase in the number of videos, the efficiency of users' browsing is reduced. This requires a technology that can effectively manage video data so that users can more effectively obtain the information they want. A video summarization is defined as a sequence of still or moving pictures that presents the main content of a video in a concise manner. [0003] At present, video summarization technology mainly considers three aspects of video redundancy, importance and coverage. Redundancy means that there is redundant information in the video, and it is n...

AI Technical Summary

Problems solved by technology

[0006] The above methods only start from a certain standard of the video summary (such as the redundancy standard or the importance standard), but do not comprehensively consider the three standards, so that the effect of the video summary does not achieve the desired effect.

Images