Image-based visual hull of a tennis racket

Abstract

Researchers are often interested in tracking object movement in sport. This could be useful to identify equipment designs that match the technique of players. Previously, stereo camera systems have been used to track markers attached to striking implements to measure their movement in three dimensions. However, manual selection of markers on the image plane can be time consuming and inaccurate. There is potential however to reduce these drawbacks associated with marker-based analysis by tracking a striking implement using its visual hull. The closest geometric approximation of an object that can be reconstructed using only its silhouette images is its visual hull. Early applications of visual hulls include size and shape estimation of objects such as stones. Recently, subject specific visual hulls constructed from multiple camera views combined with anatomical tracking algorithms have measured human motion through markerless motion capture. However, multiple camera systems are not practical for real play conditions in most sports. The application of visual hulls to measure movements of striking implements used in sport has not yet been explored. A set of calibrated views of a tennis racket were captured and segmented into binary images to obtain silhouettes. The visual hull of a tennis racket was constructed by intersection of the volume of space formed by back-projecting the silhouettes from all input views. This research is the first stage in the development of a system that measures movement of a striking implement in real play conditions by combining its visual hull with footage from a single camera.