Computer Vision Techniques for Multi-Athlete Detection, Pose Tracking and Real-Time Coaching Support

This survey reviewed the techniques needed for camera-based coaching support: person detection, multi-person tracking, pose estimation and movement analysis, along with existing sports systems and datasets. Good methods exist for each step, but reliable tracking of each athlete, sport-specific checking and ethical use are still open problems. These findings guide the design and testing plan of Athletix AI and show where more research is needed.

[1]  Z. Cao, G. Hidalgo, T. Simon, S.-E. Wei, and Y. Sheikh, “OpenPose: Realtime multi-person 2D pose estimation using part affinity fields,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 1, pp. 172–186, 2021. [2]  C. Lugaresi et al., “MediaPipe: A framework for building perception pipelines,” arXiv:1906.08172, 2019. [3]  Y. Zhang et al., “ByteTrack: Multi-object tracking by associating every detection box,” in Proc. ECCV, 2022. [4]  G. Thomas, R. Gade, T. B. Moeslund, P. Carr, and A. Hilton, “Computer vision for sports: Current applications and research topics,” Comput. Vis. Image Underst., vol. 159, pp. 3–18, 2017. [5]  J. Wang, K. Qiu, H. Peng, J. Fu, and J. Zhu, “AI Coach: Deep human pose estimation and analysis for personalized athletic training assistance,” in Proc. ACM Multimedia, 2019.