A Novel Macro-Micro Approach for Swimming Analysis in Main Swimming Techniques Using IMU Sensors

Mahdi Hamidi Rad; Vincent Gremeaux; Farzin Dadashi; Kamiar Aminian

doi:10.3389/fbioe.2020.597738

A Novel Macro-Micro Approach for Swimming Analysis in Main Swimming Techniques Using IMU Sensors

Front Bioeng Biotechnol. 2021 Jan 14:8:597738. doi: 10.3389/fbioe.2020.597738. eCollection 2020.

Authors

Mahdi Hamidi Rad¹, Vincent Gremeaux^{2

3}, Farzin Dadashi⁴, Kamiar Aminian¹

Affiliations

¹ Laboratory of Movement Analysis and Measurement, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
² Institute of Sport Sciences, University of Lausanne, Lausanne, Switzerland.
³ Sport Medicine Unit, Division of Physical Medicine and Rehabilitation, Swiss Olympic Medical Center, Lausanne University Hospital, Lausanne, Switzerland.
⁴ Gait Up S.A., Lausanne, Switzerland.

Abstract

Inertial measurement units (IMU) are proven as efficient tools for swimming analysis by overcoming the limits of video-based systems application in aquatic environments. However, coaches still believe in the lack of a reliable and easy-to-use analysis system for swimming. To provide a broad view of swimmers' performance, this paper describes a new macro-micro analysis approach, comprehensive enough to cover a full training session, regardless of the swimming technique. Seventeen national level swimmers (5 females, 12 males, 19.6 ± 2.1 yrs) were equipped with six IMUs and asked to swim 4 × 50 m trials in each swimming technique (i.e., frontcrawl, breaststroke, butterfly, and backstroke) in a 25 m pool, in front of five 2-D cameras (four under water and one over water) for validation. The proposed approach detects swimming bouts, laps, and swimming technique in macro level and swimming phases in micro level on all sensor locations for comparison. Swimming phases are the phases swimmers pass from wall to wall (wall push-off, glide, strokes preparation, swimming, and turn) and micro analysis detects the beginning of each phase. For macro analysis, an overall accuracy range of 0.83-0.98, 0.80-1.00, and 0.83-0.99 were achieved, respectively, for swimming bouts detection, laps detection and swimming technique identification on selected sensor locations, the highest being achieved with sacrum. For micro analysis, we obtained the lowest error mean and standard deviation on sacrum for the beginning of wall-push off, glide and turn (-20 ± 89 ms, 4 ± 100 ms, 23 ± 97 ms, respectively), on shank for the beginning of strokes preparation (0 ± 88 ms) and on wrist for the beginning of swimming (-42 ± 72 ms). Comparing the swimming techniques, sacrum sensor achieves the smallest range of error mean and standard deviation during micro analysis. By using the same macro-micro approach across different swimming techniques, this study shows its efficiency to detect the main events and phases of a training session. Moreover, comparing the results of both macro and micro analyses, sacrum has achieved relatively higher amounts of accuracy and lower mean and standard deviation of error in all swimming techniques.

Keywords: lap segmentation; macro-micro analysis; sports biomechanics; swimming; wearable sensor.