Swimming Stroke Phase Segmentation Based on Wearable Motion Capture Technique

Wearable motion capture technique is widely used in kinematic analysis, which contributes to understanding motion patterns and provides quantitative data on human postures. Swimming stroke phase plays an important role in spatial-temporal swimming parameters. As a sporting pattern that involves all limbs, the swimming phase is more complicated than gait phase and makes the swimming phase segmentation a new issue of pattern recognition. This article focuses on the swimming phase segmentation as pattern classification. By analyzing the human posture data given by motion capture system, swimming phase could be described qualitatively and used to obtain posture features. The swimming phase of the four competitive swimming styles is studied in this article and classified accurately. In the tenfold cross-validation, the mean values of accuracy, sensitivity, and specificity could reach 98.22%, 95.65%, and 98.67%, respectively, under the 2.5-ms timing tolerance. In terms of leave-one-subject-out cross-validation, performance metrics perform best under a relatively small timing tolerance. The results of the experiment show that the study could well-address the issue of swimming phase segmentation and provide spatial-temporal parameters for further swimming motion analysis.