IPSN’19, April 2019, Montreal, Canada Hongyang Zhao, Shuangquan Wang, Gang Zhou, and Woosub Jung
In addition to these research works, there are also some com-
mercial products on the market that assess the performance of
the players, such as Zepp [
41
], Usense [
32
], Babolat Play [
24
], and
Babolat Pure Drive [
7
]. These products either integrate the motion
sensors inside the racket [
7
], or require users to attach the motion
sensors onto the racket [
41
] [
32
] [
24
]. They analyze the tennis data
and compute the key performance metrics for each swing, such as
stroke type, ball speed, ball spin, and sweet spot. However, none of
these commercial products opens their algorithms to the public. In
addition, we compare our proposed ball speed calculation algorithm
with the ball speed calculation algorithm in Zepp. The evaluation
results show that our algorithm is more accurate than that in Zepp.
6 CONCLUSION
In this paper, we propose TennisEye, a tennis ball speed calculation
system using a racket-mounted sensor. It detects tennis strokes,
recognizes stroke types, and calculates the ball speed. We propose
a regression model to estimate the serve speed. In addition, we
propose two models, a regression model and a physical model,
to estimate the groundstroke and volley ball speed for beginner
and advanced players, respectively. For the leave-one-subject-out
cross-validation test, experiments with human subjects show that
the TennisEye is 10.8% more accurate than the state-of-the-art
work. TennisEye is promising and has commercial potential as it
is lightweight and more accurate than the existing commercial
product.
REFERENCES
[1]
Amin Ahmadi, Edmond Mitchell, Francois Destelle, Marc Gowing, Noel E
O’Connor, Chris Richter, and Kieran Moran. 2014. Automatic activity classica-
tion and movement assessment during a sports training session using wearable
inertial sensors. In Proceedings of the IEEE BSN. IEEE, 98–103.
[2]
Akash Anand, Manish Sharma, Rupika Srivastava, Lakshmi Kaligounder, and
Divya Prakash. 2017. Wearable Motion Sensor Based Analysis of Swing Sports.
In Proceedings of the IEEE ICMLA. IEEE, 261–267.
[3]
Peter Blank, Benjamin H Groh, and Bjoern M Eskoer. 2017. Ball speed and spin
estimation in table tennis using a racket-mounted inertial sensor. In Proceedings
of the ACM ISWC. ACM, 2–9.
[4]
Howard Brody. 1997. The physics of tennis. III. The ball–racket interaction.
American Journal of Physics 65, 10 (1997), 981–987.
[5]
Lars Büthe, Ulf Blanke, Haralds Capkevics, and Gerhard Tröster. 2016. A wearable
sensing system for timing analysis in tennis. In Proceedings of the IEEE BSN. IEEE,
43–48.
[6]
Carl De Boor, Carl De Boor, Etats-Unis Mathématicien, Carl De Boor, and Carl
De Boor. 1978. A practical guide to splines. Vol. 27. Springer.
[7]
Babolat Pure Drive. 2019. https://www.babolat.us/product/tennis/generic/
pure-drive-play-102229.
[8]
Hawk eye innovations. 2018. http://www.hawkeyeinnovations.co.uk/sports/
tennis.
[9]
Biyi Fang, Nicholas D Lane, Mi Zhang, and Fahim Kawsar. 2016. Headscan: A
wearable system for radio-based sensing of head and mouth-related activities. In
Proceedings of the ACM/IEEE IPSN. IEEE, 1–12.
[10]
Benjamin H Groh, Frank Warschun, Martin Deininger, Thomas Kautz, Christine
Martindale, and Bjoern M Eskoer. 2017. Automated ski velocity and jump
length determination in ski jumping based on unobtrusive and wearable sensors.
Proceedings of the ACM IMWUT 1, 3 (2017), 53.
[11]
Mark Hall, Eibe Frank, Georey Holmes, Bernhard Pfahringer, Peter Reutemann,
and Ian H Witten. 2009. The WEKA data mining software: an update. Proceedings
of the ACM SIGKDD 11, 1 (2009), 10–18.
[12]
Tian Hao, Guoliang Xing, and Gang Zhou. 2015. RunBuddy: a smartphone
system for running rhythm monitoring. In Proceedings of the ACM Ubicomp.
ACM, 133–144.
[13]
Global Wearable Devices in Sports Market. 2018. https://www.
researchandmarkets.com/research/k8p2gz/global_wearable?w=4.
[14]
Aftab Khan, James Nicholson, and Thomas Plötz. 2017. Activity Recognition for
Quality Assessment of Batting Shots in Cricket using a Hierarchical Representa-
tion. Proceedings of the ACM IMWUT 1, 3 (2017), 62.
[15]
Cassim Ladha, Nils Y Hammerla, Patrick Olivier, and Thomas Plötz. 2013.
ClimbAX: skill assessment for climbing enthusiasts. In Proceedings of the ACM
Ubicomp. ACM, 235–244.
[16]
Industrial Wearable Devices Market. 2018. https://www.researchandmarkets.
com/research/nrtbv9/global_industrial?w=4.
[17]
Miha Mlakar and Mitja Luštrek. 2017. Analyzing tennis game through sensor
data with machine learning and multi-objective optimization. In Proceedings of
the ACM ISWC. ACM, 153–156.
[18]
Frank Mokaya, Roland Lucas, Hae Young Noh, and Pei Zhang. 2016. Burnout: a
wearable system for unobtrusive skeletal muscle fatigue estimation. In Proceedings
of the ACM/IEEE IPSN. IEEE, 1–12.
[19]
Andreas Möller, Luis Roalter, Stefan Diewald, Johannes Scherr, Matthias Kranz,
Nils Hammerla, Patrick Olivier, and Thomas Plötz. 2012. Gymskill: A personal
trainer for physical exercises. In Proceedings of the IEEE PerCom. IEEE, 213–220.
[20]
Conservation of Linear Momentum. 2018. https://en.wikipedia.org/wiki/
Momentum.
[21]
NEIL Owens, C Harris, and C Stennett. 2003. Hawk-eye tennis system. In Pro-
ceedings of the IET VIE. IET, 182–185.
[22]
Weiping Pei, Jun Wang, Xubin Xu, Zhengwei Wu, and Xiaorong Du. 2017. An
embedded 6-axis sensor based recognition for tennis stroke. In Proceedings of the
IEEE ICCE. IEEE, 55–58.
[23]
Gopal Pingali, Agata Opalach, and Yves Jean. 2000. Ball tracking and virtual
replays for innovative tennis broadcasts. In Proceedings of the IEEE Pattern Recog-
nition, Vol. 4. IEEE, 152–156.
[24] Babolat Play. 2019. http://en.babolatplay.com/play.
[25] PlaySight. 2018. http://playsight.com/.
[26]
Tayeba Qazi, Prerana Mukherjee, Siddharth Srivastava, Brejesh Lall, and
Nathi Ram Chauhan. 2015. Automated ball tracking in tennis videos. In Proceed-
ings of the IEEE ICIIP. IEEE, 236–240.
[27] J Ross Quinlan. 2014. C4. 5: programs for machine learning. Elsevier.
[28]
Manish Sharma, Rupika Srivastava, Akash Anand, Divya Prakash, and Lakshmi
Kaligounder. 2017. Wearable motion sensor based phasic analysis of tennis serve
for performance feedback. In Proceedings of the IEEE ICASSP. IEEE, 5945–5949.
[29] Sony. 2019. https://www.sony.com.au/microsite/tennis/.
[30] Least squares. 2018. https://en.wikipedia.org/wiki/Least_squares.
[31]
Rupika Srivastava, Ayush Patwari, Sunil Kumar, Gaurav Mishra, Laksmi
Kaligounder, and Purnendu Sinha. 2015. Ecient characterization of tennis
shots and game analysis using wearable sensors data. In Proceedings of the IEEE
SENSORS. IEEE, 1–4.
[32] Usense. 2018. http://www.ubc-tech.com/en/index.html.
[33]
Qizhi Wang, KangJie Zhang, and Dengdian Wang. 2014. The trajectory prediction
and analysis of spinning ball for a table tennis robot application. In Proceedings
of the IEEE CYBER. IEEE, 496–501.
[34]
Xinyu Wei, Patrick Lucey, Stuart Morgan, and Sridha Sridharan. 2013. Predicting
shot locations in tennis using spatiotemporal data. In Proceedings of the IEEE
DICTA. IEEE, 1–8.
[35]
Xinyu Wei, Patrick Lucey, Stuart Morgan, and Sridha Sridharan. 2013. Sweet-spot:
Using spatiotemporal data to discover and predict shots in tennis. In Proceedings
of the Annual MIT Sloan Sports Analytics Conference.
[36] Xinyu Wei, Patrick Lucey, Stephen Vidas, Stuart Morgan, and Sridha Sridharan.
2014. Forecasting events using an augmented hidden conditional random eld.
In Proceedings of the Springer ACCV. Springer, 569–582.
[37]
Graham Weir and Peter McGavin. 2008. The coecient of restitution for the
idealized impact of a spherical, nano-scale particle on a rigid plane. In Proceedings
of the Royal Society of London A: Mathematical, Physical and Engineering Sciences,
Vol. 464. The Royal Society, 1295–1307.
[38]
David Whiteside, Olivia Cant, Molly Connolly, and Machar Reid. 2017. Monitoring
hitting load in tennis using inertial sensors and machine learning. International
journal of sports physiology and performance 12, 9 (2017), 1212–1217.
[39]
Fei Yan, W Christmas, and Josef Kittler. 2005. A tennis ball tracking algorithm
for automatic annotation of tennis match. In Proceedings of the BMVC, Vol. 2.
619–628.
[40]
Disheng Yang, Jian Tang, Yang Huang, Chao Xu, Jinyang Li, Liang Hu, Guobin
Shen, Chieh-Jan Mike Liang, and Hengchang Liu. 2017. TennisMaster: an IMU-
based online serve performance evaluation system. In Proceedings of the ACM
AH. ACM, 17.
[41] Zepp. 2018. http://www.zepp.com/tennis/.
[42]
Shibo Zhang, William Stogin, and Nabil Alshurafa. 2018. I sense overeating:
Motif-based machine learning framework to detect overeating using wrist-worn
sensing. Information Fusion 41 (2018), 37–47.
[43]
Hongyang Zhao, Shuangquan Wang, Gang Zhou, and Daqing Zhang. 2018.
Ultigesture: A Wristband-based Platform for Continuous Gesture Control in
Healthcare. Smart Health (2018).
[44]
Bo Zhou, Harald Koerger, Markus Wirth, Constantin Zwick, Christine Martin-
dale, Heber Cruz, Bjoern Eskoer, and Paul Lukowicz. 2016. Smart soccer shoe:
monitoring foot-ball interaction with shoe integrated textile pressure sensor
matrix. In Proceedings of the ACM ISWC. ACM, 64–71.