05 / 2022 – 11 / 2022
The game of golf has seen a steady increase in player count in the last decade, with 2021 exhibiting the largest influx of new players in the last decade . Despite the golf swing being one of the most complex motions known to man and the wider commercial availability of dedicated coaching technology (such as “Trackman”), analysis and coaching by a professional has remained the industry standard.
A variety of software in the form of apps have been developed with the intent of aiding professionals in their analysis and coaching of a player (e.g., “V1 Golf“ (over 1 million downloads (PlayStore), “CoachNow” (over 100.000 downloads (PlayStore), “133t Golf Training” (over 10.000 downloads (PlayStore))). With machine learning based algorithms becoming increasingly established, previous academic endeavors have shown possible applications of AI in golf swing analysis .
The 3D movement pattern of the golf swing can already be recorded with high accuracy. The current gold standard is 3D kinematography , however, single-view video  and inertial measurement units [5,6] have also been employed. There is also parallel research at FAU  as well as internationally  regarding the use of radar- and other EM-wave-based sensing for movement analysis. Still, all these methods have not found wide-spread adoption in human or AI-driven coaching practice.
Some apps targeting individual golfers seem to have recognized the potential of AI for this task and claim to rely on it at least partially (e.g., “Golf Boost AI: Swing Analyzer” (over 10.000 downloads via PlayStore, “Swingbot Golf Swing Analysis” (over 1000 downloads via PlayStore)).
The purpose of the proposed work is to research whether recent contributions in AI-driven marker-free biomechanical motion analysis based on single-view (or multi-view) video are applicable in golf swing analysis as well as improvement.
 Annual statistics published by the Deutscher Golf Verband e.V., 30.09.2021, https://serviceportal.dgv-intranet.de/files/pdf2/7-a2200043-dgv_statistiken.pdf
 U. Johansson, R. König, P. Brattberg, A. Dahlbom and M. Riveiro, “Mining Trackman Golf Data,” 2015 International Conference on Computational Science and Computational Intelligence (CSCI), 2015, pp. 380-385, doi: 10.1109/CSCI.2015.77.
 B. M. Nigg, G. K. Cole, I. C. Wright. “Optical methods”, in: Biomechanics of the musculo-skeletal system, B. M. Nigg and W. Herzog Eds., 3rd ed. New Jersey, NJ, John Wiley & Sons, ch. 3.6, 302-331, 2007.
 R. Urtasun, D. J. Fleet, P. Fua. Monocular 3–D Tracking of the Golf Swing. Proceedings of the Computer Vision and Pattern Recognition Conference, 932-938, 2005.
 R. Burchfield, S. Venkatesan. A Framework for Golf Training Using Low-Cost Inertial Sensors. In Proc. of the BSN 2010, Singapore, 267–272, 2012.
 U. Jensen, P. Kugler, F. Dassler, B. Eskofier. Sensor-based Instant Golf Putt Feedback. In Proc. of the IACSS 2011, Shanghai, 49–53, 2011.
 www.empkins.de, accessed 20.03.2022.
 F. Adib, C. Hsu, H Mao, D. Katabi, F. Durand. Capturing the Human Figure through a Wall. ACM Transactions on Graphics. 34(6), 1–13, 2015.