Share Email Print
cover

Proceedings Paper

Swimmer detection and pose estimation for continuous stroke-rate determination
Author(s): Dan Zecha; Thomas Greif; Rainer Lienhart
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this work we propose a novel approach to automatically detect a swimmer and estimate his/her pose continuously in order to derive an estimate of his/her stroke rate given that we observe the swimmer from the side. We divide a swimming cycle of each stroke into several intervals. Each interval represents a pose of the stroke. We use specifically trained object detectors to detect each pose of a stroke within a video and count the number of occurrences per time unit of the most distinctive poses (so-called key poses) of a stroke to continuously infer the stroke rate. We extensively evaluate the overall performance and the influence of the selected poses for all swimming styles on a data set consisting of a variety of swimmers.

Paper Details

Date Published: 10 February 2012
PDF: 13 pages
Proc. SPIE 8304, Multimedia on Mobile Devices 2012; and Multimedia Content Access: Algorithms and Systems VI, 830410 (10 February 2012); doi: 10.1117/12.908309
Show Author Affiliations
Dan Zecha, Univ. of Augsburg (Germany)
Thomas Greif, Univ. of Augsburg (Germany)
Rainer Lienhart, Univ. of Augsburg (Germany)


Published in SPIE Proceedings Vol. 8304:
Multimedia on Mobile Devices 2012; and Multimedia Content Access: Algorithms and Systems VI
Cees G. M. Snoek; Nicu Sebe; Lyndon Kennedy; Reiner Creutzburg; David Akopian, Editor(s)

© SPIE. Terms of Use
Back to Top