Single view silhouette fitting techniques for estimating tennis racket position

Elliott, N, Choppin, S, Goodwill, S, Senior, T, Hart, J and Allen, TB ORCID: https://orcid.org/0000-0003-4910-9149 (2017) Single view silhouette fitting techniques for estimating tennis racket position. Sports Engineering, 21 (2). pp. 137-147. ISSN 1369-7072

Preview

Published Version Available under License Creative Commons Attribution. Download (5MB) | Preview

Abstract

Stereo camera systems have been used to track markers attached to a racket, allowing its position to be obtained in three-dimensional (3D) space. Typically, markers are manually selected on the image plane, but this can be time-consuming. A markerless system based on one stationary camera estimating 3D racket position data is desirable for research and play. The markerless method presented in this paper relies on a set of racket silhouette views in a common reference frame captured with a calibrated camera and a silhouette of a racket captured with a camera whose relative pose is outside the common reference frame. The aim of this paper is to provide validation of these single view fitting techniques to estimate the pose of a tennis racket. This includes the development of a calibration method to provide the relative pose of a stationary camera with respect to a racket. Mean static racket position was reconstructed to within ±2 mm. Computer generated camera poses and silhouette views of a full size racket model were used to demonstrate the potential of the method to estimate 3D racket position during a simplified serve scenario. From a camera distance of 14 m, 3D racket position was estimated providing a spatial accuracy of 1.9 ± 0.14 mm, similar to recent 3D video marker tracking studies of tennis.