TY - GEN
T1 - Cost-Efficient and Bias-Robust Sports Player Tracking by Integrating GPS and Video
AU - Kim, Hyunsung
AU - Kim, Chang Jo
AU - Jeong, Minchul
AU - Lee, Jaechan
AU - Yoon, Jinsung
AU - Ko, Sang Ki
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Player tracking data are now widely used in the sports industry to provide deeper insights to domain participants. Global positioning systems (GPS) and camera-based optical tracking systems (OTS) are two common tracking systems, but the former suffers from location biases and the latter requires either a heavy installment of multiple cameras or a lot of manual correction work. Overcoming these weaknesses of individual systems, we propose a framework for cost-efficient and bias-robust player tracking by integrating GPS and video data. We design a sophisticated filtering algorithm to selectively use the positional information from bounding boxes detected in the video and use the GPS data as a reliable tool for identifying the chosen boxes. Using the player identity and location information of these bounding boxes, we estimate and remove GPS biases in two steps to obtain unbiased player trajectories. We demonstrate that our algorithm precisely tracks players from video with the aid of GPS data even in poor conditions such as the presence of player occlusions and players outside the sight of cameras.
AB - Player tracking data are now widely used in the sports industry to provide deeper insights to domain participants. Global positioning systems (GPS) and camera-based optical tracking systems (OTS) are two common tracking systems, but the former suffers from location biases and the latter requires either a heavy installment of multiple cameras or a lot of manual correction work. Overcoming these weaknesses of individual systems, we propose a framework for cost-efficient and bias-robust player tracking by integrating GPS and video data. We design a sophisticated filtering algorithm to selectively use the positional information from bounding boxes detected in the video and use the GPS data as a reliable tool for identifying the chosen boxes. Using the player identity and location information of these bounding boxes, we estimate and remove GPS biases in two steps to obtain unbiased player trajectories. We demonstrate that our algorithm precisely tracks players from video with the aid of GPS data even in poor conditions such as the presence of player occlusions and players outside the sight of cameras.
KW - GPS-OTS integration
KW - Global positioning system
KW - Multiple object tracking
KW - Signal processing
KW - Sports player tracking
UR - http://www.scopus.com/inward/record.url?scp=85149815341&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-27527-2_6
DO - 10.1007/978-3-031-27527-2_6
M3 - Conference contribution
AN - SCOPUS:85149815341
SN - 9783031275265
T3 - Communications in Computer and Information Science
SP - 74
EP - 86
BT - Machine Learning and Data Mining for Sports Analytics - 9th International Workshop, MLSA 2022, Revised Selected Papers
A2 - Brefeld, Ulf
A2 - Davis, Jesse
A2 - Van Haaren, Jan
A2 - Zimmermann, Albrecht
PB - Springer Science and Business Media Deutschland GmbH
T2 - 9th International Workshop on Machine Learning and Data Mining for Sports Analytics, MLSA 2022, co-located with the 21st Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 202
Y2 - 19 September 2022 through 19 September 2022
ER -