Detection of Players on a Soccer Team based on Informed Filters using Only Color Features

Takuro Oki, Ryusuke Miyamoto

Abstract

Recently, semantic analysis of sports videos has become an active research topic. In particular, player detection on the field is an important technique for various applications, such as calculations of distance covered by a player during a soccer game that are essential for semantic event detection and tactical analysis. Tracab is one of the most famous systems that can visualize the statistics of players’ performance during the game. However, the current detection and tracking systems used for Tracab are very large and expensive, therefore they are only found at large stadiums. This system is also required by many major teams in order to play a match. To solve this problem, we tackled this task by using a simple monocular camera and proposed an high accurate soccer player detection method with only color features in (Miyamoto and Oki, 2016). This method is based on a simple sliding window algorithm, however it does not use background subtraction and inter-frame difference. This is because they are not appropriate for moving cameras, though we require our system to operate properly for aerial photographs taken by drones. In (Miyamoto and Oki, 2016), we tried to found all humans on the field including coaches and referees. However, for team tactics and player activity analysis, it is more useful to detect only players that belong to a certain team. Therefore, in this paper, we improve (Miyamoto and Oki, 2016) method and try to enable accurate detection of soccer players based on their belonging teams.

References

  1. ChyronHego (2003). Tracab optical tracking. http:// chyronhego.com/sports-data/tracab.
  2. Miyamoto, R. and Oki, T. (2016). Soccer player detection with only color features selected using informed haarlike features. In Advanced Concepts for Intelligent Vision Systems. to be published.
  3. Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., volume 1, pages 511-518.
  4. Zhang, S., Bauckhage, C., and Cremers, A. (2014). Informed haar-like features improve pedestrian detection. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 947-954.
  5. Zhang, S., Benenson, R., and Schiele, B. (2015). Filtered channel features for pedestrian detection. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 1751-1760.
Download


Paper Citation


in Harvard Style

Oki T. and Miyamoto R. (2016). Detection of Players on a Soccer Team based on Informed Filters using Only Color Features . In - icSPORTS, ISBN , pages 0-0


in Bibtex Style

@conference{icsports16,
author={Takuro Oki and Ryusuke Miyamoto},
title={Detection of Players on a Soccer Team based on Informed Filters using Only Color Features},
booktitle={ - icSPORTS,},
year={2016},
pages={},
publisher={SciTePress},
organization={INSTICC},
doi={},
isbn={},
}


in EndNote Style

TY - CONF
JO - - icSPORTS,
TI - Detection of Players on a Soccer Team based on Informed Filters using Only Color Features
SN -
AU - Oki T.
AU - Miyamoto R.
PY - 2016
SP - 0
EP - 0
DO -