Particle filter with least square fitting prediction and spatial relationship based multi-view elimination for 3D Volleyball players tracking

Shuyi Huang, Xizhou Zhuang, Norikazu Ikoma, Masaaki Honda, Takeshi Ikenaga

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

6 Citations (Scopus)

Abstract

Multiple players tracking in volleyball video analysis is very important for developing applications such as tactical analysis system. To obtain a high success rate of tracking, frequent occlusion among players is a problem to be solved. This paper proposes a least square fitting prediction model and a spatial relationship based multi-view elimination method based on a particle filter scheme in 3D space. The prediction model applies a least square fitting to positions in several previous time steps, which can predict player's position during occlusion accurately. The elimination method eliminates other players' regions based on distances between camera and players' positions, which distinguishes players separately and avoids feature loss in severe occlusion. Experiments conducted on videos of the Final Game of 2014 Japan Inter High School Games of Men's Volleyball in Tokyo Metropolitan Gymnasium show that this multiple players tracking algorithm achieves an average tracking success rate of 97.05%.

Original languageEnglish
Title of host publicationProceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages28-31
Number of pages4
ISBN (Electronic)9781467387804
DOIs
Publication statusPublished - 2016 Jul 18
Event12th IEEE International Colloquium on Signal Processing and its Applications, CSPA 2016 - Melaka, Malaysia
Duration: 2016 Mar 42016 Mar 6

Other

Other12th IEEE International Colloquium on Signal Processing and its Applications, CSPA 2016
CountryMalaysia
CityMelaka
Period16/3/416/3/6

Fingerprint

Least Square Fitting
Particle Filter
Elimination
Occlusion
Prediction
Prediction Model
Cameras
Game
Video Analysis
Systems Analysis
Japan
Eliminate
Camera
Experiments
Predict
Relationships
Experiment

Keywords

  • 3D tracking
  • multi-object tracking
  • occlusion
  • particle filter

ASJC Scopus subject areas

  • Signal Processing
  • Control and Systems Engineering
  • Control and Optimization

Cite this

Huang, S., Zhuang, X., Ikoma, N., Honda, M., & Ikenaga, T. (2016). Particle filter with least square fitting prediction and spatial relationship based multi-view elimination for 3D Volleyball players tracking. In Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016 (pp. 28-31). [7515797] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSPA.2016.7515797

Particle filter with least square fitting prediction and spatial relationship based multi-view elimination for 3D Volleyball players tracking. / Huang, Shuyi; Zhuang, Xizhou; Ikoma, Norikazu; Honda, Masaaki; Ikenaga, Takeshi.

Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 28-31 7515797.

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

Huang, S, Zhuang, X, Ikoma, N, Honda, M & Ikenaga, T 2016, Particle filter with least square fitting prediction and spatial relationship based multi-view elimination for 3D Volleyball players tracking. in Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016., 7515797, Institute of Electrical and Electronics Engineers Inc., pp. 28-31, 12th IEEE International Colloquium on Signal Processing and its Applications, CSPA 2016, Melaka, Malaysia, 16/3/4. https://doi.org/10.1109/CSPA.2016.7515797
Huang S, Zhuang X, Ikoma N, Honda M, Ikenaga T. Particle filter with least square fitting prediction and spatial relationship based multi-view elimination for 3D Volleyball players tracking. In Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 28-31. 7515797 https://doi.org/10.1109/CSPA.2016.7515797
Huang, Shuyi ; Zhuang, Xizhou ; Ikoma, Norikazu ; Honda, Masaaki ; Ikenaga, Takeshi. / Particle filter with least square fitting prediction and spatial relationship based multi-view elimination for 3D Volleyball players tracking. Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 28-31
@inproceedings{231cb730b34f4dc1b46c6c7356378849,
title = "Particle filter with least square fitting prediction and spatial relationship based multi-view elimination for 3D Volleyball players tracking",
abstract = "Multiple players tracking in volleyball video analysis is very important for developing applications such as tactical analysis system. To obtain a high success rate of tracking, frequent occlusion among players is a problem to be solved. This paper proposes a least square fitting prediction model and a spatial relationship based multi-view elimination method based on a particle filter scheme in 3D space. The prediction model applies a least square fitting to positions in several previous time steps, which can predict player's position during occlusion accurately. The elimination method eliminates other players' regions based on distances between camera and players' positions, which distinguishes players separately and avoids feature loss in severe occlusion. Experiments conducted on videos of the Final Game of 2014 Japan Inter High School Games of Men's Volleyball in Tokyo Metropolitan Gymnasium show that this multiple players tracking algorithm achieves an average tracking success rate of 97.05{\%}.",
keywords = "3D tracking, multi-object tracking, occlusion, particle filter",
author = "Shuyi Huang and Xizhou Zhuang and Norikazu Ikoma and Masaaki Honda and Takeshi Ikenaga",
year = "2016",
month = "7",
day = "18",
doi = "10.1109/CSPA.2016.7515797",
language = "English",
pages = "28--31",
booktitle = "Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Particle filter with least square fitting prediction and spatial relationship based multi-view elimination for 3D Volleyball players tracking

AU - Huang, Shuyi

AU - Zhuang, Xizhou

AU - Ikoma, Norikazu

AU - Honda, Masaaki

AU - Ikenaga, Takeshi

PY - 2016/7/18

Y1 - 2016/7/18

N2 - Multiple players tracking in volleyball video analysis is very important for developing applications such as tactical analysis system. To obtain a high success rate of tracking, frequent occlusion among players is a problem to be solved. This paper proposes a least square fitting prediction model and a spatial relationship based multi-view elimination method based on a particle filter scheme in 3D space. The prediction model applies a least square fitting to positions in several previous time steps, which can predict player's position during occlusion accurately. The elimination method eliminates other players' regions based on distances between camera and players' positions, which distinguishes players separately and avoids feature loss in severe occlusion. Experiments conducted on videos of the Final Game of 2014 Japan Inter High School Games of Men's Volleyball in Tokyo Metropolitan Gymnasium show that this multiple players tracking algorithm achieves an average tracking success rate of 97.05%.

AB - Multiple players tracking in volleyball video analysis is very important for developing applications such as tactical analysis system. To obtain a high success rate of tracking, frequent occlusion among players is a problem to be solved. This paper proposes a least square fitting prediction model and a spatial relationship based multi-view elimination method based on a particle filter scheme in 3D space. The prediction model applies a least square fitting to positions in several previous time steps, which can predict player's position during occlusion accurately. The elimination method eliminates other players' regions based on distances between camera and players' positions, which distinguishes players separately and avoids feature loss in severe occlusion. Experiments conducted on videos of the Final Game of 2014 Japan Inter High School Games of Men's Volleyball in Tokyo Metropolitan Gymnasium show that this multiple players tracking algorithm achieves an average tracking success rate of 97.05%.

KW - 3D tracking

KW - multi-object tracking

KW - occlusion

KW - particle filter

UR - http://www.scopus.com/inward/record.url?scp=84983475371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983475371&partnerID=8YFLogxK

U2 - 10.1109/CSPA.2016.7515797

DO - 10.1109/CSPA.2016.7515797

M3 - Conference contribution

SP - 28

EP - 31

BT - Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -