文章基本信息

标题：Soccer Event Detection
本地全文：下载
作者：Abdullah Khan ; Beatrice Lazzerini ; Gaetano Calabrese 等
期刊名称：Computer Science & Information Technology
电子版ISSN：2231-5403
出版年度：2018
卷号：8
期号：5
页码：119-129
DOI：10.5121/csit.2018.80509
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：The research community is interested in developing automatic systems for the detection ofevents in video. This is particularly important in the field of sports data analytics. This paperpresents an approach for identifying major complex events in soccer videos, starting fromobject detection and spatial relations between objects. The proposed framework, firstly, detectsobjects from each single video frame providing a set of candidate objects with associatedconfidence scores. The event detection system, then, detects events by means of rules which arebased on temporal and logical combinations of the detected objects and their relative distances.The effectiveness of the framework is preliminary demonstrated over different events like "Ballpossession" and "Kicking the ball".
关键词：Event detection in video; simple events; complex events.