Sports video collection intelligent generation and distribution method based on 5G MEC

Abstract

The invention discloses a sports video collection intelligent generation and distribution method based on 5G MEC, and the method comprises the steps: taking sports equipment as a detection main body for positioning a key frame, and taking a segment from the start moment to the end moment of an action as wonderful clip where the key frame is located; recognizing a human face of a person doing an action in the key frame from the wonderful clips shot by a plurality of video acquisition devices in the same time period, and comparing the recognized human face with a human face image in a user database to judge whether the wonderful clips belong to a user or not; and a local MEC server of each video acquisition device distributes the wonderful clip collection exclusive to the user to the MEC server which responds to the user request most frequently in the past, and the local MEC server of the user responds to the wonderful clips collection when the user requests to check the exclusive clip collection content of the user. According to the invention, the pressure of a central server can be reduced, the link delay can be reduced, the wonderful clips in the sports video can be positioned, the exclusive wonderful collection for each user can be generated, and the attention and interest of the user can be attracted.

Description

Technical field[0001]The present invention relates to the technical field of video image processing, in particular to a method for intelligently generating and distributing sports video highlights based on 5G MEC.Background technique[0002]With the development of the Internet, stadiums tend to be intelligently constructed. A large number of monitoring equipment is installed in the venue, and the monitoring equipment generates a large amount of video data. First, processing these data consumes a lot of server resources. Secondly, it is also very important for venues to dig out some clips from these video data centers to attract users' attention and interest.[0003]In the past, the processing of surveillance video was done by a central server. A large amount of worthless content in surveillance video increased the pressure on the central server. The arrival of 5G brought us into the era of Internet of Everything. Mobile Edge Computing (MEC) concept first appeared in 2013. At that time, ...

AI Technical Summary

Problems solved by technology

[0004] In the existing technology, events are often used as the main body for identification and editing, and it is not possible to generate highlight highlights for the user. Only the event video is intercepted and played, which cannot meet the personalized needs of users to watch their own sports video highlights.

Moreover, in the prior art, a central server is used instead of multi-access edge computing technology, and all video clips and highlights are generated in the central server. When the video stream is large, the load on the central server will be too large. link delay increase

Images