CUED Publications database

Virtual tracking shots for sports analysis

Bennett, S and Lasenby, J and Purnell, T (2016) Virtual tracking shots for sports analysis. Electronic Imaging, Computer Vision Applications in Sports, 2017. pp. 4-9.

Full text not available from this repository.


Reviewing athletic performance is a critical part of modern sports training, but snapshots only showing part of a course or exercise can be misleading, while travelling cameras are expensive. In this paper we describe a system merging the output of many autonomous inexpensive camera nodes distributed around a course to reliably synthesize tracking shots of multiple athletes training concurrently. Issues such as uncontrolled lighting, athlete occlusions and overtaking/pack-motion are dealt with, as is compensating for the quirks of cheap image sensors. The resultant system is entirely automated, inexpensive, scalable and provides output in near real-time, allowing coaching staff to give immediate and relevant feedback on a performance. Requiring no alteration to existing training exercises has boosted the system's uptake by coaches, with over 100,000 videos recorded to date.

Item Type: Article
Uncontrolled Keywords: software rail camera sports analysis subject tracking video stitching virtual tracking shot
Divisions: Div F > Signal Processing and Communications
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 20:02
Last Modified: 18 Feb 2021 18:06
DOI: 10.2352/ISSN.2470-1173.2017.16.CVAS-342