首页 | 本学科首页   官方微博 | 高级检索  
     


Semantic annotation of soccer videos: automatic highlights identification
Authors:Jürgen Assfalg  Marco Bertini  Carlo Colombo  Alberto Del Bimbo  Walter Nunziati
Affiliation:Dipartimento di Sistemi e Informatica, Via S. Marta 3, Firenze 50139, Italy
Abstract:Automatic semantic annotation of video streams allows both to extract significant clips for production logging and to index video streams for posterity logging. Automatic annotation for production logging is particularly demanding, as it is applied to non-edited video streams and must rely only on visual information. Moreover, annotation must be computed in quasi real-time. In this paper, we present a system that performs automatic annotation of the principal highlights in soccer video, suited for both production and posterity logging. The knowledge of the soccer domain is encoded into a set of finite state machines, each of which models a specific highlight. Highlight detection exploits visual cues that are estimated from the video stream, and particularly, ball motion, the currently framed playfield zone, players’ positions and colors of players’ uniforms. The highlight models are checked against the current observations, using a model checking algorithm. The system has been developed within the EU ASSAVID project.
Keywords:Semantic annotation  Sports videos  Highlights detection
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号