Tennis video analysis using transformed motion vector field

Peng Wang; Rui Cai; Bin Li; Shi Qiang Yang

Tennis video analysis using transformed motion vector field

Peng Wang
, Rui Cai
, Bin Li
, Shi Qiang Yang

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

The motion estimated from tennis video is unable to analyze player's true movement due to the diagonally located camera and the high noises. In this paper, a transform algorithm of Motion Vector Field (MVF) is proposed to revise the deformed motion vector based on the pinhole camera model. In this algorithm, the techniques of foreground object mask and global motion compensation are incorporated to reduce noises. Previous methods based on MVF analysis are further utilized to recognize basic actions of either tennis player. And, the experiments on live broadcasted tennis videos show very encouraging results.

Original language	English
Pages (from-to)	935-938
Number of pages	4
Journal	Tien Tzu Hsueh Pao/Acta Electronica Sinica
Volume	33
Issue number	5
State	Published - May 2005
Externally published	Yes

Keywords

Pinhole camera modeling
Tennis video analysis
Transform algorithm of motion vector field

Cite this

@article{72b05b64c080446fa71e9c90c8e41873,

title = "Tennis video analysis using transformed motion vector field",

abstract = "The motion estimated from tennis video is unable to analyze player's true movement due to the diagonally located camera and the high noises. In this paper, a transform algorithm of Motion Vector Field (MVF) is proposed to revise the deformed motion vector based on the pinhole camera model. In this algorithm, the techniques of foreground object mask and global motion compensation are incorporated to reduce noises. Previous methods based on MVF analysis are further utilized to recognize basic actions of either tennis player. And, the experiments on live broadcasted tennis videos show very encouraging results.",

keywords = "Pinhole camera modeling, Tennis video analysis, Transform algorithm of motion vector field",

author = "Peng Wang and Rui Cai and Bin Li and Yang, \{Shi Qiang\}",

year = "2005",

month = may,

language = "English",

volume = "33",

pages = "935--938",

journal = "Tien Tzu Hsueh Pao/Acta Electronica Sinica",

issn = "0372-2112",

publisher = "Chinese Institute of Electronics",

number = "5",

}

TY - JOUR

T1 - Tennis video analysis using transformed motion vector field

AU - Wang, Peng

AU - Cai, Rui

AU - Li, Bin

AU - Yang, Shi Qiang

PY - 2005/5

Y1 - 2005/5

N2 - The motion estimated from tennis video is unable to analyze player's true movement due to the diagonally located camera and the high noises. In this paper, a transform algorithm of Motion Vector Field (MVF) is proposed to revise the deformed motion vector based on the pinhole camera model. In this algorithm, the techniques of foreground object mask and global motion compensation are incorporated to reduce noises. Previous methods based on MVF analysis are further utilized to recognize basic actions of either tennis player. And, the experiments on live broadcasted tennis videos show very encouraging results.

AB - The motion estimated from tennis video is unable to analyze player's true movement due to the diagonally located camera and the high noises. In this paper, a transform algorithm of Motion Vector Field (MVF) is proposed to revise the deformed motion vector based on the pinhole camera model. In this algorithm, the techniques of foreground object mask and global motion compensation are incorporated to reduce noises. Previous methods based on MVF analysis are further utilized to recognize basic actions of either tennis player. And, the experiments on live broadcasted tennis videos show very encouraging results.

KW - Pinhole camera modeling

KW - Tennis video analysis

KW - Transform algorithm of motion vector field

UR - https://www.scopus.com/pages/publications/22844453167

M3 - Article

AN - SCOPUS:22844453167

SN - 0372-2112

VL - 33

SP - 935

EP - 938

JO - Tien Tzu Hsueh Pao/Acta Electronica Sinica

JF - Tien Tzu Hsueh Pao/Acta Electronica Sinica

IS - 5

ER -

Tennis video analysis using transformed motion vector field

Abstract

Keywords

Fingerprint

Cite this