Open AccessResearch on Detecting Moving Objects in Football Match Video
Author(s) -
Hongyi Xu,
Jiaqi Lu,
Qun He,
Lei Gu,
Chengliang Feng
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1651/1/012161
Subject(s) - football , computer science , computer vision , kalman filter , event (particle physics) , artificial intelligence , face (sociological concept) , process (computing) , field (mathematics) , multimedia , mathematics , social science , physics , quantum mechanics , sociology , pure mathematics , operating system , political science , law
In recent years, detecting moving objects in video has attracted extensive attention in the field of computer vision and pattern recognition. With football becoming one of the most popular sports, analyzing the process of football games is of commercial value and guiding significance. However, the previous research mainly focused on the event detection, and rarely on getting the trajectory of moving objects by directly extracting from the video. This article discussed the method of detecting moving objects in the football match video. We extract the marker lines and build the coordinate system based on LUV color space. And we use the 68 landmarks to recognize the human face and the Kalman filter approach to detect the football. Our research is aimed at helping the audience and football professionals in analyzing the player performance and team strategy.