Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes

Weicun XU; Qingjie ZHAO; Yuxia WANG; Xuanya LI

doi:10.1587/transinf.E97.D.119

Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes

Weicun XU, Qingjie ZHAO, Yuxia WANG, Xuanya LI

Full Text Views

0

Share
Cite this

Summary :

Soccer player tracking and labeling suffer from the similar appearance of the players in the same team, especially in long-shot scenes where the faces and the numbers of the players are too blurry to identify. In this paper, we propose an efficient multi-player tracking system. The tracking system takes the detection responses of a human detector as inputs. To realize real-time player detection, we generate a spatial proposal to minimize the scanning scope of the detector. The tracking system utilizes the discriminative appearance models trained using the online Boosting method to reduce data-association ambiguity caused by the appearance similarity of the players. We also propose to build an online learned player recognition model which can be embedded in the tracking system to approach online player recognition and labeling in tracking applications for long-shot scenes by two stages. At the first stage, to build the model, we utilize the fast k-means clustering method instead of classic k-means clustering to build and update a visual word vocabulary in an efficient online manner, using the informative descriptors extracted from the training samples drawn at each time step of multi-player tracking. The first stage finishes when the vocabulary is ready. At the second stage, given the obtained visual word vocabulary, an incremental vector quantization strategy is used to recognize and label each tracked player. We also perform importance recognition validation to avoid mistakenly recognizing an outlier, namely, people we do not need to recognize, as a player. Both quantitative and qualitative experimental results on the long-shot video clips of a real soccer game video demonstrate that, the proposed player recognition model performs much better than some state-of-the-art online learned models, and our tracking system also performs quite effectively even under very complicated situations.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.1 pp.119-129

Publication Date: 2014/01/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E97.D.119

Type of Manuscript: PAPER

Category: Pattern Recognition

Authors

Weicun XU
  Beijing Institute of Technology
Qingjie ZHAO
  Beijing Institute of Technology
Yuxia WANG
  Beijing Institute of Technology
Xuanya LI
  Chinese Academy of Sciences

Keyword

soccer player recognition, player tracking and labeling, online learning, visual words, fast k-means clustering

Cite this

Copy

Weicun XU, Qingjie ZHAO, Yuxia WANG, Xuanya LI, "Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 1, pp. 119-129, January 2014, doi: 10.1587/transinf.E97.D.119.
Abstract: Soccer player tracking and labeling suffer from the similar appearance of the players in the same team, especially in long-shot scenes where the faces and the numbers of the players are too blurry to identify. In this paper, we propose an efficient multi-player tracking system. The tracking system takes the detection responses of a human detector as inputs. To realize real-time player detection, we generate a spatial proposal to minimize the scanning scope of the detector. The tracking system utilizes the discriminative appearance models trained using the online Boosting method to reduce data-association ambiguity caused by the appearance similarity of the players. We also propose to build an online learned player recognition model which can be embedded in the tracking system to approach online player recognition and labeling in tracking applications for long-shot scenes by two stages. At the first stage, to build the model, we utilize the fast k-means clustering method instead of classic k-means clustering to build and update a visual word vocabulary in an efficient online manner, using the informative descriptors extracted from the training samples drawn at each time step of multi-player tracking. The first stage finishes when the vocabulary is ready. At the second stage, given the obtained visual word vocabulary, an incremental vector quantization strategy is used to recognize and label each tracked player. We also perform importance recognition validation to avoid mistakenly recognizing an outlier, namely, people we do not need to recognize, as a player. Both quantitative and qualitative experimental results on the long-shot video clips of a real soccer game video demonstrate that, the proposed player recognition model performs much better than some state-of-the-art online learned models, and our tracking system also performs quite effectively even under very complicated situations.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E97.D.119/_p

Copy

@ARTICLE{e97-d_1_119,
author={Weicun XU, Qingjie ZHAO, Yuxia WANG, Xuanya LI, },
journal={IEICE TRANSACTIONS on Information},
title={Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes},
year={2014},
volume={E97-D},
number={1},
pages={119-129},
abstract={Soccer player tracking and labeling suffer from the similar appearance of the players in the same team, especially in long-shot scenes where the faces and the numbers of the players are too blurry to identify. In this paper, we propose an efficient multi-player tracking system. The tracking system takes the detection responses of a human detector as inputs. To realize real-time player detection, we generate a spatial proposal to minimize the scanning scope of the detector. The tracking system utilizes the discriminative appearance models trained using the online Boosting method to reduce data-association ambiguity caused by the appearance similarity of the players. We also propose to build an online learned player recognition model which can be embedded in the tracking system to approach online player recognition and labeling in tracking applications for long-shot scenes by two stages. At the first stage, to build the model, we utilize the fast k-means clustering method instead of classic k-means clustering to build and update a visual word vocabulary in an efficient online manner, using the informative descriptors extracted from the training samples drawn at each time step of multi-player tracking. The first stage finishes when the vocabulary is ready. At the second stage, given the obtained visual word vocabulary, an incremental vector quantization strategy is used to recognize and label each tracked player. We also perform importance recognition validation to avoid mistakenly recognizing an outlier, namely, people we do not need to recognize, as a player. Both quantitative and qualitative experimental results on the long-shot video clips of a real soccer game video demonstrate that, the proposed player recognition model performs much better than some state-of-the-art online learned models, and our tracking system also performs quite effectively even under very complicated situations.},
keywords={},
doi={10.1587/transinf.E97.D.119},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes
T2 - IEICE TRANSACTIONS on Information
SP - 119
EP - 129
AU - Weicun XU
AU - Qingjie ZHAO
AU - Yuxia WANG
AU - Xuanya LI
PY - 2014
DO - 10.1587/transinf.E97.D.119
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2014
AB - Soccer player tracking and labeling suffer from the similar appearance of the players in the same team, especially in long-shot scenes where the faces and the numbers of the players are too blurry to identify. In this paper, we propose an efficient multi-player tracking system. The tracking system takes the detection responses of a human detector as inputs. To realize real-time player detection, we generate a spatial proposal to minimize the scanning scope of the detector. The tracking system utilizes the discriminative appearance models trained using the online Boosting method to reduce data-association ambiguity caused by the appearance similarity of the players. We also propose to build an online learned player recognition model which can be embedded in the tracking system to approach online player recognition and labeling in tracking applications for long-shot scenes by two stages. At the first stage, to build the model, we utilize the fast k-means clustering method instead of classic k-means clustering to build and update a visual word vocabulary in an efficient online manner, using the informative descriptors extracted from the training samples drawn at each time step of multi-player tracking. The first stage finishes when the vocabulary is ready. At the second stage, given the obtained visual word vocabulary, an incremental vector quantization strategy is used to recognize and label each tracked player. We also perform importance recognition validation to avoid mistakenly recognizing an outlier, namely, people we do not need to recognize, as a player. Both quantitative and qualitative experimental results on the long-shot video clips of a real soccer game video demonstrate that, the proposed player recognition model performs much better than some state-of-the-art online learned models, and our tracking system also performs quite effectively even under very complicated situations.
ER -