Coordination-model-based method for obtaining video abstract

Abstract

The invention, which belongs to the video processing technology, particularly relates to a coordination-model-based method for obtaining a video abstract. The method comprises: (1), generating a feature expression matrix of a video frame; (2), evaluating significance of the video frame comprehensively by a coordination mode; and (3), extracting a key frame to form a video abstract. According to the invention, with construction of the coordination model, expressivity and dispersity of the video frame are considered, so that accuracy of the video abstract is improved. Constraint information of the geometric structure of the video frame is added into the dictionary learning process, so that sparse representation becomes accurate and expressivity of the video frame can be measured accurately. With a dispersity measuring standard based on similarity measurement, redundant frame extraction can be avoided, thereby improving conciseness of the video abstract.

Description

technical field [0001] The invention belongs to video processing technology, and in particular relates to a method for acquiring video summaries based on a collaborative model, which can be used in the fields of public security monitoring management, military reconnaissance, and large-scale video data management. Background technique [0002] In recent years, with the increasing popularity of low-cost and large-capacity digital video recording equipment, video data is growing explosively at an alarming rate. Take YouTube, the largest video website in the world, as an example. As of January 2015, the total duration of videos uploaded every minute is 100 hours. This makes understanding and obtaining the main content of the video in a manual viewing method need to consume a huge amount of manpower and time. Therefore, people urgently need a technology that can efficiently analyze massive video data. Several video frames (called key frames) containing the main content of the o...

AI Technical Summary

Problems solved by technology

[0005] Although these methods achieved good results, they did not consider the relationship between adjacent frames when performing dictionary learning.

This will not only not guarantee that similar adjacent frames have similar sparse expression coefficients, but also cannot guarantee that the sparse expression coefficients of dissimilar adjacent frames must be different

Therefore, the accuracy of sparse representation will suffer

In addition, although these methods focus on the expressiveness of video frames, they ignore the dispersion of video frames, which leads to the selection of key frames that tend to contain redundant information and cannot effectively cover all important content.

Images