Video key frame extraction algorithm

Abstract

The invention discloses a video key frame extraction algorithm, and belongs to the technical field of information security. According to the algorithm, firstly the black border width of the horizontaldirection and the black border height of the vertical direction of a certain frame in the current input video stream and the width and height of the effective image area of the frame are calculated;then the feature information of the effective image area of the frame is calculated and compared with that of the last frame so as to calculate the degree of difference; when the degree of differenceis greater than the threshold, the data in the difference frame are compared with each frame of data of a cache area so as to calculate the similarity of the frame; and when the similarity of the difference frame is greater than the threshold, the difference frame is regarded to be similar to the certain frame in the cache area, one non-difference frame is added, the maximum cumulative number of the non-difference frame is reached, the frame is outputted as the difference frame and written in the cache area, statistics of the variance value of the Y value and the variance value of the UY valueof the frame is performed and the key frame and the blank frame are outputted. The algorithm is realized by the C programming language and can be applied to multi-video and multi-thread calling so that the algorithm is high in adaptability and efficient and rapid.

Description

technical field [0001] The invention belongs to the technical field of information security, and relates to the extraction of video content information, specifically, a video key frame extraction algorithm. Background technique [0002] With the application and popularization of Internet, multimedia information retrieval system has more and more influence on various fields of society. Traditional information retrieval uses a text-based retrieval method, and text features need to be explained when querying, requiring users to have a certain degree of accuracy and standardization in describing text features. However, due to the rich connotation of video data and the subjectivity of people's extraction of video content, it is difficult to describe video information with a few keywords. Therefore, content-based video retrieval came into being. [0003] The traditional content-based video retrieval method uses video as a collection of frame images, and uses the image retrieval ...

AI Technical Summary

Problems solved by technology

[0003] The traditional content-based video retrieval method uses video as a collection of frame images, and uses the image retrieval method to retrieve frame by frame. The disadvantage of this method is that it needs to process a large amount of image information, which causes great difficulties in information transmission and calculation.

Images