A System for Acquisition and Modelling of Ice-Hockey Stick Shape Deformation From Player Shot Videos

Kaustubha Mendhurwar, Gaurav Handa, Leixiao Zhu, Sudhir Mudur, Etienne Beauchesne, Marc LeVangie, Aiden Hallihan, Abbas Javadtalab, Tiberiu Popa; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 890-891

Abstract


In Ice-Hockey, a player shot significantly deforms the hockey-stick. Since this deformation plays a dynamic role in determining the flight of the puck, it is used in the study of hockey stick shapes, material properties, match to player style, etc. Reconstructing the deformable 3D shape of the stick during the course of a player shot has important applications. In this work we present a new, low cost, portable system to acquire videos of a player shot and to automatically reconstruct the deformation in 3D shape of the stick.The point clouds obtained are low resolution and noisy, as it is difficult to separate players hand geometry from the stick.We use the medial axis to constrain the point cloud to stick only geometry, and then use physics-based co-rotational FEM to determine the stick bend. We have tested the system with different sticks, players and shot styles, and our system yields accurate reconstructions. The results are discussed both qualitatively and where possible, quantitatively.

Related Material


[pdf] [video]
[bibtex]
@InProceedings{Mendhurwar_2020_CVPR_Workshops,
author = {Mendhurwar, Kaustubha and Handa, Gaurav and Zhu, Leixiao and Mudur, Sudhir and Beauchesne, Etienne and LeVangie, Marc and Hallihan, Aiden and Javadtalab, Abbas and Popa, Tiberiu},
title = {A System for Acquisition and Modelling of Ice-Hockey Stick Shape Deformation From Player Shot Videos},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020}
}