A Video Summarization Method Based on Spatial-Temporal Recombination of Events

Abstract

The invention provides a video abstraction generation method based on space-time recombination of active events. According to the method, an original video is pre-treated, blank frames are removed, and the video after pretreatment is subjected to structured analysis as follows: moving targets in the original video are taken as an object, videos of all key moving target events are extracted, time correlation between the moving target events is weakened, and time sequence recombination is performed on the moving target events based on the principle that activity ranges are not conflicted; meanwhile, background images are extracted reasonably based on the reference of the visual perception of a user, and a delayed dynamic background video is generated; and finally, the moving target events and the delayed dynamic background video are sutured seamlessly, a video abstraction with short time, concise content and comprehensive information is formed, and a plurality of moving targets can occur simultaneously in the finally generated video abstraction. The video abstraction generation method can generate the video abstraction used for video browsing or searching efficiently and rapidly, and the video abstraction can express semantic information of the video more reasonably and better meets the visual perception of the user.

Description

Technical field [0001] The present invention relates to an intelligent analysis technology, specifically, to a video summary generation method based on spatio-temporal reorganization of activity events, and belongs to the technical field of computer artificial intelligence, digital video image processing, and video monitoring or video retrieval. [0002] technical background [0003] In the field of social public security, video surveillance systems have become an important technical means to maintain public order and strengthen social management. Thousands of surveillance cameras are set up in the streets and alleys of the city, and on different occasions in various enterprises and undertakings to perform their missions of non-stop video recording. These massive video files are characterized by a large amount of stored data and a long time. It takes a lot of manpower, material resources and time to find relevant clues through video recording, and the efficiency is extremely low. ...

AI Technical Summary

Problems solved by technology

[0006] The commonality of the above two video summaries is that they must strictly follow the chronological order and achieve the purpose of quickly browsing the video at the cost of losing a large amount of activity information. Therefore, they cannot express the semantic information of the video well, and cannot be applied to the scene of surveillance video.

Images