Multi-view 3D ball tracking with abrupt motion adaptive system model, anti-occlusion observation and spatial density based recovery in sports analysis

Xina Cheng, Norikazu Ikoma, Masaaki Honda, Takeshi Ikenaga

研究成果: Article

5 引用 (Scopus)

抄録

Significant challenges in ball tracking of sports analysis by computer vision technology are: 1) accuracy of estimated 3D ball trajectory under difficult conditions; 2) external forces added by players lead to irregular motions of the ball; 3) unpredictable situations in the real game, i.e. the ball occluded by players and other objects, complex background and changing lighting condition. With the goal of multi-view 3D ball tracking, this paper proposes an abrupt motion adaptive system model, an anti-occlusion observation model, and a spatial density-based automatic recovery based on particle filter. The system model combines two different system noises that cover the motion of the ball both in general situation and situation subject to abrupt motion caused by external force. Combination ratio of these two noises and number of particles are adaptive to the estimated motion by weight distribution of particles. The anti-occlusion observation model evaluates image feature of each camera and eliminates influence of the camera with less confidence. The spatial density, which is calculated based on 3D ball candidates filtered out by spatial homographic relationship between cameras, is proposed for generating new set of particles to recover the tracking when tracking failure is detected. Experimental results based on HDTV video sequences (2014 Inter High School Men's Volleyball Games, Japan), which were captured by four cameras located at each corner of the court, show that the success rate achieved by the proposals of 3D ball tracking is 99.42%.

元の言語English
ページ(範囲)1215-1225
ページ数11
ジャーナルIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
E100A
発行部数5
DOI
出版物ステータスPublished - 2017 5 1

Fingerprint

Adaptive systems
Adaptive Systems
Sports
Occlusion
Ball
Recovery
Cameras
Motion
Camera
High definition television
Model
Computer vision
Lighting
Trajectories
Game
Weight Distribution
Observation
Particle Filter
Japan
Computer Vision

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Applied Mathematics
  • Electrical and Electronic Engineering

これを引用

@article{283f1d08b8554c04954fd43281851d9d,
title = "Multi-view 3D ball tracking with abrupt motion adaptive system model, anti-occlusion observation and spatial density based recovery in sports analysis",
abstract = "Significant challenges in ball tracking of sports analysis by computer vision technology are: 1) accuracy of estimated 3D ball trajectory under difficult conditions; 2) external forces added by players lead to irregular motions of the ball; 3) unpredictable situations in the real game, i.e. the ball occluded by players and other objects, complex background and changing lighting condition. With the goal of multi-view 3D ball tracking, this paper proposes an abrupt motion adaptive system model, an anti-occlusion observation model, and a spatial density-based automatic recovery based on particle filter. The system model combines two different system noises that cover the motion of the ball both in general situation and situation subject to abrupt motion caused by external force. Combination ratio of these two noises and number of particles are adaptive to the estimated motion by weight distribution of particles. The anti-occlusion observation model evaluates image feature of each camera and eliminates influence of the camera with less confidence. The spatial density, which is calculated based on 3D ball candidates filtered out by spatial homographic relationship between cameras, is proposed for generating new set of particles to recover the tracking when tracking failure is detected. Experimental results based on HDTV video sequences (2014 Inter High School Men's Volleyball Games, Japan), which were captured by four cameras located at each corner of the court, show that the success rate achieved by the proposals of 3D ball tracking is 99.42{\%}.",
keywords = "Abrupt motion, Multi-view 3D ball tracking, Occlusion, Sports analysis, Tracking recover",
author = "Xina Cheng and Norikazu Ikoma and Masaaki Honda and Takeshi Ikenaga",
year = "2017",
month = "5",
day = "1",
doi = "10.1587/transfun.E100.A.1215",
language = "English",
volume = "E100A",
pages = "1215--1225",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "5",

}

TY - JOUR

T1 - Multi-view 3D ball tracking with abrupt motion adaptive system model, anti-occlusion observation and spatial density based recovery in sports analysis

AU - Cheng, Xina

AU - Ikoma, Norikazu

AU - Honda, Masaaki

AU - Ikenaga, Takeshi

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Significant challenges in ball tracking of sports analysis by computer vision technology are: 1) accuracy of estimated 3D ball trajectory under difficult conditions; 2) external forces added by players lead to irregular motions of the ball; 3) unpredictable situations in the real game, i.e. the ball occluded by players and other objects, complex background and changing lighting condition. With the goal of multi-view 3D ball tracking, this paper proposes an abrupt motion adaptive system model, an anti-occlusion observation model, and a spatial density-based automatic recovery based on particle filter. The system model combines two different system noises that cover the motion of the ball both in general situation and situation subject to abrupt motion caused by external force. Combination ratio of these two noises and number of particles are adaptive to the estimated motion by weight distribution of particles. The anti-occlusion observation model evaluates image feature of each camera and eliminates influence of the camera with less confidence. The spatial density, which is calculated based on 3D ball candidates filtered out by spatial homographic relationship between cameras, is proposed for generating new set of particles to recover the tracking when tracking failure is detected. Experimental results based on HDTV video sequences (2014 Inter High School Men's Volleyball Games, Japan), which were captured by four cameras located at each corner of the court, show that the success rate achieved by the proposals of 3D ball tracking is 99.42%.

AB - Significant challenges in ball tracking of sports analysis by computer vision technology are: 1) accuracy of estimated 3D ball trajectory under difficult conditions; 2) external forces added by players lead to irregular motions of the ball; 3) unpredictable situations in the real game, i.e. the ball occluded by players and other objects, complex background and changing lighting condition. With the goal of multi-view 3D ball tracking, this paper proposes an abrupt motion adaptive system model, an anti-occlusion observation model, and a spatial density-based automatic recovery based on particle filter. The system model combines two different system noises that cover the motion of the ball both in general situation and situation subject to abrupt motion caused by external force. Combination ratio of these two noises and number of particles are adaptive to the estimated motion by weight distribution of particles. The anti-occlusion observation model evaluates image feature of each camera and eliminates influence of the camera with less confidence. The spatial density, which is calculated based on 3D ball candidates filtered out by spatial homographic relationship between cameras, is proposed for generating new set of particles to recover the tracking when tracking failure is detected. Experimental results based on HDTV video sequences (2014 Inter High School Men's Volleyball Games, Japan), which were captured by four cameras located at each corner of the court, show that the success rate achieved by the proposals of 3D ball tracking is 99.42%.

KW - Abrupt motion

KW - Multi-view 3D ball tracking

KW - Occlusion

KW - Sports analysis

KW - Tracking recover

UR - http://www.scopus.com/inward/record.url?scp=85019003017&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019003017&partnerID=8YFLogxK

U2 - 10.1587/transfun.E100.A.1215

DO - 10.1587/transfun.E100.A.1215

M3 - Article

AN - SCOPUS:85019003017

VL - E100A

SP - 1215

EP - 1225

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 5

ER -