Introduction: Sports analytics using advanced sensors is introduced actively into competitive sports. In competitive sports` team, formation assessment of the team is essential in order to achieve advantageous situations in games. However, the accuracies of conventional position measurement technologies such as GPS and video analytics are insufficient. Therefore, the aim of this study is to develop a technology that has better position measurement accuracy. Methods: To investigate the necessary accuracy for formation assessment of the team, we conducted interviews with experts in professional teams. Followings are the requirements set by the experts. (1) Accuracy of players` position measurement < 10 cm error (2) Accuracy of personal identification > 90% We considered the new position measurement method combining with Laser Radar and acceleration sensor. The advantage of using Laser Radar is that the error in position measurement is less than 10 cm. However, it is not able to identify individuals. Another method for personal identification is necessary. Then, we found out that players` speed measured by the Laser Radar is associated with energy consumption measured by wearable acceleration sensor. The proposed method measures the trajectories of identified individuals by performing the matching based on similarities. Evaluation We performed an experiment to assess the accuracy of the proposed method. Specifically, we calculated the matching rate between the personal trajectories identified by the proposed method and the actual personal trajectories that were assigned visually. The experiment was carried out on a 3-on-3 passing game called `Ballschule` that has movements that common with major team sports. We measured a total of 130 trajectories in these games. Results: The proposed system accurately identified the individuals in 119/130 trajectories, and the accuracy of personal identification is 91.5%. The accuracy of more than 90% was achieved while keeping the error in players` position measurements of less than 10 cm. Conclusion: This study shows that a new method to measure personal trajectories with high accuracy by combining with Laser Radar System and acceleration sensors. Acknowledgement This research is partially supported by the Center of Innovation Program from Japan Science and Technology Agency, JST.
© Copyright 2016 21st Annual Congress of the European College of Sport Science (ECSS), Vienna, 6. -9. July 2016. Veröffentlicht von University of Vienna. Alle Rechte vorbehalten.