Embedded programming and real-time signal processing of swimming strokes

Abstract

The research outlined in this paper was conducted to allow real-time processing, transmission and presentation of data to swimming coaches and subsequently their swimmers in a training environment, focused on providing information relevant to strokes in free swimming. This was achieved using a wearable wireless sensor and embedded programming techniques, using accelerations involved in the swimming stroke to provide relevant features for coaches. Current methods used do not offer real-time response to coaches, which results in the lack of real-time feedback and significantly increased post-session analysis time. Filtering and signal processing algorithms are described here, which allow real-time data analysis to be embedded within a wireless sensor node. The system significantly reduces the time for processing acquired data and has delivered a novel monitoring device suitable for operation within the harsh environment of the pool.

Assessment of three-dimensional joint kinematics of the upper limb during simulated swimming using wearable inertial-magnetic measurement units

“…Recently, wearable inertial-magnetic measurement units (IMMUs) have been used (Magalhaes, Vannozzi, Gatta, & Fantozzi, 2015). Initially, stroke rate, stroke phases analysis and discrimination among different swimming styles were performed (Dadashi et al, 2013;Le Sage et al, 2011;Ohgi, Ichikawa, Homma, & Miyaji, 2003). Subsequently, the velocity, attitude and position of the swimmer were estimated to have specific performance indicators for the whole length of the swimming pool (Dadashi, Crettenand, Millet, & Aminian, 2012;Stamm, James, & Thiel, 2013).…”

Application of Video-Based Methods for Competitive Swimming Analysis: A Systematic Review

“…A recent study reported that it took approximately seven and a half hours to carry out manual digitization of a relatively small amount of footage, involving ten swimmers performing three dives each. 70 Magalhaes, et al 71 also cite another example whereby it took 27 hours to digitize footage of four separate stroke cycles for one swimmer, involving images from six cameras, 19 anatomical landmarks and 1,620 frames in total.…”

Image Based Stroke-Rate Detection System for Swim Race Analysis

“…Collection of performance parameters during training rather than competition allows the use of alternative measurement techniques such as wireless accelerometers or inertial sensors [8][9][10]. These systems offer real-time feedback and valuable velocity data of the swimmers, but unfortunately are not able to be used in competitive environments.…”