Event state based particle filter for ball event detection in volleyball game analysis

Xina Cheng, Norikazu Ikoma, Masaaki Honda, Takeshi Ikenaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The ball state tracking and detection technology plays a significant role in volleyball game analysis for volleyball team supporting and tactics development. This paper proposes a ball event detection method to achieve high detection rate by solving challenges including: the great variety of event length, the large intra-class difference of one event and the influence caused by ball trajectories. Proposed state vector covers both the event type and the event period length so that the system model can transits various lengths of event period and predicts event types by volleyball game rules. The curve segmental observation model avoids the tracking error influence to evaluate the event period likelihood by referring neighbouring trajectories of the ball. And according to the standard of the ball event, the feature of the distance between the ball and specific court line are extracted to evaluate the ball event type in observation. At last a two-layer estimation method estimates the posterior state which is a joint probability distribution. Experiments of the proposed method implemented on 3D trajectories tracked from multi-view volleyball game videos shows the detection rate reaches 90.43%.

Original languageEnglish
Title of host publication20th International Conference on Information Fusion, Fusion 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9780996452700
DOIs
Publication statusPublished - 2017 Aug 11
Event20th International Conference on Information Fusion, Fusion 2017 - Xi'an, China
Duration: 2017 Jul 102017 Jul 13

Other

Other20th International Conference on Information Fusion, Fusion 2017
CountryChina
CityXi'an
Period17/7/1017/7/13

Fingerprint

Event Detection
games
Particle Filter
balls
Ball
Trajectories
Game
filters
Probability distributions
Trajectory
trajectories
tactics
Video Games
Evaluate
Experiments
state vectors
Joint Distribution
transit
Likelihood
Probability Distribution

Keywords

  • event detection
  • particle filter
  • volleyball game analysis

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing
  • Modelling and Simulation
  • Instrumentation
  • Numerical Analysis

Cite this

Cheng, X., Ikoma, N., Honda, M., & Ikenaga, T. (2017). Event state based particle filter for ball event detection in volleyball game analysis. In 20th International Conference on Information Fusion, Fusion 2017 - Proceedings [8009806] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ICIF.2017.8009806

Event state based particle filter for ball event detection in volleyball game analysis. / Cheng, Xina; Ikoma, Norikazu; Honda, Masaaki; Ikenaga, Takeshi.

20th International Conference on Information Fusion, Fusion 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. 8009806.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cheng, X, Ikoma, N, Honda, M & Ikenaga, T 2017, Event state based particle filter for ball event detection in volleyball game analysis. in 20th International Conference on Information Fusion, Fusion 2017 - Proceedings., 8009806, Institute of Electrical and Electronics Engineers Inc., 20th International Conference on Information Fusion, Fusion 2017, Xi'an, China, 17/7/10. https://doi.org/10.23919/ICIF.2017.8009806
Cheng X, Ikoma N, Honda M, Ikenaga T. Event state based particle filter for ball event detection in volleyball game analysis. In 20th International Conference on Information Fusion, Fusion 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. 8009806 https://doi.org/10.23919/ICIF.2017.8009806
Cheng, Xina ; Ikoma, Norikazu ; Honda, Masaaki ; Ikenaga, Takeshi. / Event state based particle filter for ball event detection in volleyball game analysis. 20th International Conference on Information Fusion, Fusion 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{cfb6f0d599c74fd99cbdfe8cade2028e,
title = "Event state based particle filter for ball event detection in volleyball game analysis",
abstract = "The ball state tracking and detection technology plays a significant role in volleyball game analysis for volleyball team supporting and tactics development. This paper proposes a ball event detection method to achieve high detection rate by solving challenges including: the great variety of event length, the large intra-class difference of one event and the influence caused by ball trajectories. Proposed state vector covers both the event type and the event period length so that the system model can transits various lengths of event period and predicts event types by volleyball game rules. The curve segmental observation model avoids the tracking error influence to evaluate the event period likelihood by referring neighbouring trajectories of the ball. And according to the standard of the ball event, the feature of the distance between the ball and specific court line are extracted to evaluate the ball event type in observation. At last a two-layer estimation method estimates the posterior state which is a joint probability distribution. Experiments of the proposed method implemented on 3D trajectories tracked from multi-view volleyball game videos shows the detection rate reaches 90.43{\%}.",
keywords = "event detection, particle filter, volleyball game analysis",
author = "Xina Cheng and Norikazu Ikoma and Masaaki Honda and Takeshi Ikenaga",
year = "2017",
month = "8",
day = "11",
doi = "10.23919/ICIF.2017.8009806",
language = "English",
booktitle = "20th International Conference on Information Fusion, Fusion 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Event state based particle filter for ball event detection in volleyball game analysis

AU - Cheng, Xina

AU - Ikoma, Norikazu

AU - Honda, Masaaki

AU - Ikenaga, Takeshi

PY - 2017/8/11

Y1 - 2017/8/11

N2 - The ball state tracking and detection technology plays a significant role in volleyball game analysis for volleyball team supporting and tactics development. This paper proposes a ball event detection method to achieve high detection rate by solving challenges including: the great variety of event length, the large intra-class difference of one event and the influence caused by ball trajectories. Proposed state vector covers both the event type and the event period length so that the system model can transits various lengths of event period and predicts event types by volleyball game rules. The curve segmental observation model avoids the tracking error influence to evaluate the event period likelihood by referring neighbouring trajectories of the ball. And according to the standard of the ball event, the feature of the distance between the ball and specific court line are extracted to evaluate the ball event type in observation. At last a two-layer estimation method estimates the posterior state which is a joint probability distribution. Experiments of the proposed method implemented on 3D trajectories tracked from multi-view volleyball game videos shows the detection rate reaches 90.43%.

AB - The ball state tracking and detection technology plays a significant role in volleyball game analysis for volleyball team supporting and tactics development. This paper proposes a ball event detection method to achieve high detection rate by solving challenges including: the great variety of event length, the large intra-class difference of one event and the influence caused by ball trajectories. Proposed state vector covers both the event type and the event period length so that the system model can transits various lengths of event period and predicts event types by volleyball game rules. The curve segmental observation model avoids the tracking error influence to evaluate the event period likelihood by referring neighbouring trajectories of the ball. And according to the standard of the ball event, the feature of the distance between the ball and specific court line are extracted to evaluate the ball event type in observation. At last a two-layer estimation method estimates the posterior state which is a joint probability distribution. Experiments of the proposed method implemented on 3D trajectories tracked from multi-view volleyball game videos shows the detection rate reaches 90.43%.

KW - event detection

KW - particle filter

KW - volleyball game analysis

UR - http://www.scopus.com/inward/record.url?scp=85029406881&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029406881&partnerID=8YFLogxK

U2 - 10.23919/ICIF.2017.8009806

DO - 10.23919/ICIF.2017.8009806

M3 - Conference contribution

BT - 20th International Conference on Information Fusion, Fusion 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -