A football video event detection and semantic annotation method based on multi-modal information fusion

Abstract

The invention discloses a multi-modal information fusion football video event detection and semantic annotation method. The multi-modal information fusion football video event detection and semantic annotation method includes the steps of detecting the event type of Internet match result report text description statements with the potential semantic analytical method; detecting football video intermediate semantic objects, dividing a site area, conducting attack-and-defense transition analysis, and determining boundaries of video event fragments; determining the match starting time according to kick-off circle and whistling detection results, and achieving initial semantic classification of attack-and-defense fragments with the Bayesian network; under the constraint of coarse-grained time information in text descriptions, achieving the football video event semantic annotation according to semantic synchronization text descriptions and video events of texts and the video fragments. By means of the method, the Internet text information and video inherent audio-visual feature analysis are fused for analyzing football videos, accuracy for detecting the video events and the boundaries of the video events is improved, the rich semantic annotation of football video contents is achieved, and a solid foundation is laid for building a video indexing mechanism based on semantics.

Description

technical field [0001] The invention belongs to the field of content-based video retrieval, and in particular relates to a football video event detection and semantic labeling method based on multimodal information fusion. Background technique [0002] With the rapid development of computer technology, storage technology and network technology, as well as the continuous updating of various digital terminals and mobile devices, the amount of video data continues to grow at an explosive rate. At the same time, since the time, place and method of obtaining information are gradually unrestricted, people's demand for video retrieval has greatly increased. How to make people quickly find the video clips they are interested in from the massive video data has become an urgent need, and the technology that can meet this demand is the content-based video retrieval (CBVR, Content Based Video) that people generally pay attention to at present. Retrieval) technology. Video annotation i...

AI Technical Summary

Problems solved by technology

However, firstly, the time information of most webcast texts is not accurate, and is generally minute-level time information; secondly, sports websites only broadcast webcast texts of important or famous international events, and many events only The post-match news report, that is to say, the webcast text is not very versatile; third, due to the unfavorable factors of the video time bar, such as transparency, position change, style change, appearing and disappearing, and low resolution, the accuracy of the video clock Recognition is still facing a greater challenge

Images