Sensors

Research

19 pages, 580 KiB

Open AccessArticle

Automatic Swimming Activity Recognition and Lap Time Assessment Based on a Single IMU: A Deep Learning Approach

by Erwan Delhaye, Antoine Bouvet, Guillaume Nicolas, João Paulo Vilas-Boas, Benoît Bideau and Nicolas Bideau

Sensors 2022, 22(15), 5786; https://doi.org/10.3390/s22155786 - 3 Aug 2022

Cited by 11 | Viewed by 4621

Abstract

This study presents a deep learning model devoted to the analysis of swimming using a single Inertial Measurement Unit (IMU) attached to the sacrum. Gyroscope and accelerometer data were collected from 35 swimmers with various expertise levels during a protocol including the four [...] Read more.

This study presents a deep learning model devoted to the analysis of swimming using a single Inertial Measurement Unit (IMU) attached to the sacrum. Gyroscope and accelerometer data were collected from 35 swimmers with various expertise levels during a protocol including the four swimming techniques. The proposed methodology took high inter- and intra-swimmer variability into account and was set up for the purpose of predicting eight swimming classes (the four swimming techniques, rest, wallpush, underwater, and turns) at four swimming velocities ranging from low to maximal. The overall F1-score of classification reached 0.96 with a temporal precision of 0.02 s. Lap times were directly computed from the classifier thanks to a high temporal precision and validated against a video gold standard. The mean absolute percentage error (MAPE) for this model against the video was 1.15%, 1%, and 4.07%, respectively, for starting lap times, middle lap times, and ending lap times. This model is a first step toward a powerful training assistant able to analyze swimmers with various levels of expertise in the context of in situ training monitoring. Full article

(This article belongs to the Special Issue Wearables and Computer Vision for Sports Motion Analysis)

► Show Figures

Figure 1

13 pages, 2858 KiB

Open AccessArticle

Validation of Instrumented Football Shoes to Measure On-Field Ground Reaction Forces

by Alexandre Karamanoukian, Jean-Philippe Boucher, Romain Labbé and Nicolas Vignais

Sensors 2022, 22(10), 3673; https://doi.org/10.3390/s22103673 - 11 May 2022

Cited by 3 | Viewed by 3238

Abstract

Ground reaction forces (GRF) have been widely studied in football to prevent injury. However, ambulatory tools are missing, posing methodological limitations. The purpose of this study was to assess the validity of an innovative football shoe measuring normal GRF (nGRF) directly on the [...] Read more.

Ground reaction forces (GRF) have been widely studied in football to prevent injury. However, ambulatory tools are missing, posing methodological limitations. The purpose of this study was to assess the validity of an innovative football shoe measuring normal GRF (nGRF) directly on the field through instrumented studs. A laboratory-based experiment was first conducted to compare nGRF obtained with the instrumented shoe (IS) to vertical GRF (vGRF) obtained with force platform (FP) data, the gold standard to measure vGRF. To this aim, three subjects performed 50 steps and 18 counter-movement jumps (CMJs). Secondly, eleven subjects completed running sprints at different velocities on a football field, as well as CMJs, while wearing the IS. Good to excellent agreement was found between the vGRF parameters measured with the FP and the nGRF measured by the IS (ICC > 0.75 for 9 out of 11 parameters). Moreover, on-field nGRF patterns demonstrated a progressive and significant increase in relation with the running velocity (p < 0.001). This study demonstrated that the IS is a highly valid tool to assess vGRF patterns on a football field. This innovative way to measure vGRF in situ could give new insights to quantify training load and detect neuromuscular fatigue. Full article

(This article belongs to the Special Issue Wearables and Computer Vision for Sports Motion Analysis)

► Show Figures

Figure 1

27 pages, 9302 KiB

Open AccessArticle

Pose2Sim: An End-to-End Workflow for 3D Markerless Sports Kinematics—Part 2: Accuracy

by David Pagnon, Mathieu Domalain and Lionel Reveret

Sensors 2022, 22(7), 2712; https://doi.org/10.3390/s22072712 - 1 Apr 2022

Cited by 20 | Viewed by 6832

Abstract

Two-dimensional deep-learning pose estimation algorithms can suffer from biases in joint pose localizations, which are reflected in triangulated coordinates, and then in 3D joint angle estimation. Pose2Sim, our robust markerless kinematics workflow, comes with a physically consistent OpenSim skeletal model, meant to mitigate [...] Read more.

Two-dimensional deep-learning pose estimation algorithms can suffer from biases in joint pose localizations, which are reflected in triangulated coordinates, and then in 3D joint angle estimation. Pose2Sim, our robust markerless kinematics workflow, comes with a physically consistent OpenSim skeletal model, meant to mitigate these errors. Its accuracy was concurrently validated against a reference marker-based method. Lower-limb joint angles were estimated over three tasks (walking, running, and cycling) performed multiple times by one participant. When averaged over all joint angles, the coefficient of multiple correlation (CMC) remained above 0.9 in the sagittal plane, except for the hip in running, which suffered from a systematic 15° offset (CMC = 0.65), and for the ankle in cycling, which was partially occluded (CMC = 0.75). When averaged over all joint angles and all degrees of freedom, mean errors were 3.0°, 4.1°, and 4.0°, in walking, running, and cycling, respectively; and range of motion errors were 2.7°, 2.3°, and 4.3°, respectively. Given the magnitude of error traditionally reported in joint angles computed from a marker-based optoelectronic system, Pose2Sim is deemed accurate enough for the analysis of lower-body kinematics in walking, cycling, and running. Full article

(This article belongs to the Special Issue Wearables and Computer Vision for Sports Motion Analysis)

► Show Figures

Graphical abstract

21 pages, 3198 KiB

Open AccessArticle

Recognizing Solo Jazz Dance Moves Using a Single Leg-Attached Inertial Wearable Device

by Sara Stančin and Sašo Tomažič

Sensors 2022, 22(7), 2446; https://doi.org/10.3390/s22072446 - 22 Mar 2022

Cited by 5 | Viewed by 2788

Abstract

We present here a method for recognising dance moves in sequences using 3D accelerometer and gyroscope signals, acquired by a single wearable device, attached to the dancer’s leg. The recognition entails dance tempo estimation, temporal scaling, a wearable device orientation-invariant coordinate system transformation, [...] Read more.

We present here a method for recognising dance moves in sequences using 3D accelerometer and gyroscope signals, acquired by a single wearable device, attached to the dancer’s leg. The recognition entails dance tempo estimation, temporal scaling, a wearable device orientation-invariant coordinate system transformation, and, finally, sliding correlation-based template matching. The recognition is independent of the orientation of the wearable device and the tempo of dancing, which promotes the usability of the method in a wide range of everyday application scenarios. For experimental validation, we considered the versatile repertoire of solo jazz dance moves. We created a database of 15 authentic solo jazz template moves using the performances of a professional dancer dancing at 120 bpm. We analysed 36 new dance sequences, performed by the professional and five recreational dancers, following six dance tempos, ranging from 120 bpm to 220 bpm with 20 bpm increment steps. The recognition F1 scores, obtained cumulatively for all moves for different tempos, ranged from 0.87 to 0.98. The results indicate that the presented method can be used to recognise repeated dance moves and to assess the dancer’s consistency in performance. In addition, the results confirm the potential of using the presented method to recognise imitated dance moves, supporting the learning process. Full article

(This article belongs to the Special Issue Wearables and Computer Vision for Sports Motion Analysis)

► Show Figures

Figure 1

15 pages, 1909 KiB

Open AccessArticle

Quantitative Analysis of Performance Recovery in Semi-Professional Football Players after the COVID-19 Forced Rest Period

by Luigi Truppa, Lorenzo Nuti, Stefano Mazzoleni, Pietro Garofalo and Andrea Mannini

Sensors 2022, 22(1), 242; https://doi.org/10.3390/s22010242 - 29 Dec 2021

Viewed by 2674

Abstract

This study proposes the instrumental analysis of the physiological and biomechanical adaptation of football players to a fatigue protocol during the month immediately after the COVID-19 lockdown, to get insights into fitness recovery. Eight male semi-professional football players took part in the study [...] Read more.

This study proposes the instrumental analysis of the physiological and biomechanical adaptation of football players to a fatigue protocol during the month immediately after the COVID-19 lockdown, to get insights into fitness recovery. Eight male semi-professional football players took part in the study and filled a questionnaire about their activity during the lockdown. At the resumption of activities, the mean heart rate and covered distances during fatiguing exercises, the normalized variations of mean and maximum exerted power in the Wingate test and the Bosco test outcomes (i.e., maximum height, mean exerted power, relative strength index, leg stiffness, contact time, and flight time) were measured for one month. Questionnaires confirmed a light-intensity self-administered physical activity. A significant effect of fatigue (Wilcoxon signed-rank test p < 0.05) on measured variables was confirmed for the four weeks. The analysis of the normalized variations of the aforementioned parameters allowed the distinguishing of two behaviors: downfall in the first two weeks, and recovery in the last two weeks. Instrumental results suggest a physiological and ballistic (i.e., Bosco test outcomes) recovery after four weeks. As concerns the explosive skills, the observational data are insufficient to show complete recovery. Full article

(This article belongs to the Special Issue Wearables and Computer Vision for Sports Motion Analysis)

► Show Figures

Figure 1

14 pages, 1393 KiB

Open AccessArticle

Dance Tempo Estimation Using a Single Leg-Attached 3D Accelerometer

by Sara Stančin and Sašo Tomažič

Sensors 2021, 21(23), 8066; https://doi.org/10.3390/s21238066 - 2 Dec 2021

Cited by 2 | Viewed by 2238

Abstract

We present a methodology that enables dance tempo estimation through the acquisition of 3D accelerometer signals using a single wearable inertial device positioned on the dancer’s leg. Our tempo estimation method is based on enhanced multiple resonators, implemented with comb feedback filters. To [...] Read more.

We present a methodology that enables dance tempo estimation through the acquisition of 3D accelerometer signals using a single wearable inertial device positioned on the dancer’s leg. Our tempo estimation method is based on enhanced multiple resonators, implemented with comb feedback filters. To validate the methodology, we focus on the versatile solo jazz dance style. Including a variety of dance moves, with different leg activation patterns and rhythmical variations, solo jazz provides for a highly critical validation environment. We consider 15 different solo jazz dance moves, with different leg activation patterns, assembled in a sequence of 5 repetitions of each, giving 65 moves altogether. A professional and a recreational dancer performed this assembly in a controlled environment, following eight dancing tempos, dictated by a metronome, and ranging from 80 bpm to 220 bpm with 20 bpm increment steps. We show that with appropriate enhancements and using single leg signals, the comb filter bank provides for accurate dance tempo estimates for all moves and rhythmical variations considered. Dance tempo estimates for the overall assembles match strongly the dictated tempo—the difference being at most 1 bpm for all measurement instances is within the limits of the established beat onset stability of the used metronome. Results further show that this accuracy is achievable for shorter dancing excerpts, comprising four dance moves, corresponding to one music phrase, and as such enables real-time feedback. By providing for a dancer’s tempo quality and consistency assessment, the presented methodology has the potential of supporting the learning process, classifying individual level of experience, and assessing overall performance. It is extendable to other dance styles and sport motion in general where cyclical patterns occur. Full article

(This article belongs to the Special Issue Wearables and Computer Vision for Sports Motion Analysis)

► Show Figures

Figure 1

13 pages, 3415 KiB

Open AccessArticle

Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments

by Jelle De Bock and Steven Verstockt

Sensors 2021, 21(22), 7619; https://doi.org/10.3390/s21227619 - 16 Nov 2021

Cited by 5 | Viewed by 2461

Abstract

Video-based trajectory analysis might be rather well discussed in sports, such as soccer or basketball, but in cycling, this is far less common. In this paper, a video processing pipeline to extract riding lines in cyclocross races is presented. The pipeline consists of [...] Read more.

Video-based trajectory analysis might be rather well discussed in sports, such as soccer or basketball, but in cycling, this is far less common. In this paper, a video processing pipeline to extract riding lines in cyclocross races is presented. The pipeline consists of a stepwise analysis process to extract riding behavior from a region (i.e., the fence) in a video camera feed. In the first step, the riders are identified by an Alphapose skeleton detector and tracked with a spatiotemporally aware pose tracker. Next, each detected pose is enriched with additional meta-information, such as rider modus (e.g., sitting on the saddle or standing on the pedals) and detected team (based on the worn jerseys). Finally, a post-processor brings all the information together and proposes ride lines with meta-information for the riders in the fence. The presented methodology can provide interesting insights, such as intra-athlete ride line clustering, anomaly detection, and detailed breakdowns of riding and running durations within the segment. Such detailed rider info can be very valuable for performance analysis, storytelling, and automatic summarization. Full article

(This article belongs to the Special Issue Wearables and Computer Vision for Sports Motion Analysis)

► Show Figures

Figure 1

27 pages, 10705 KiB

Open AccessArticle

Pose2Sim: An End-to-End Workflow for 3D Markerless Sports Kinematics—Part 1: Robustness

by David Pagnon, Mathieu Domalain and Lionel Reveret

Sensors 2021, 21(19), 6530; https://doi.org/10.3390/s21196530 - 30 Sep 2021

Cited by 27 | Viewed by 7892

Abstract

Being able to capture relevant information about elite athletes’ movement “in the wild” is challenging, especially because reference marker-based approaches hinder natural movement and are highly sensitive to environmental conditions. We propose Pose2Sim, a markerless kinematics workflow that uses OpenPose 2D pose detections [...] Read more.

Being able to capture relevant information about elite athletes’ movement “in the wild” is challenging, especially because reference marker-based approaches hinder natural movement and are highly sensitive to environmental conditions. We propose Pose2Sim, a markerless kinematics workflow that uses OpenPose 2D pose detections from multiple views as inputs, identifies the person of interest, robustly triangulates joint coordinates from calibrated cameras, and feeds those to a 3D inverse kinematic full-body OpenSim model in order to compute biomechanically congruent joint angles. We assessed the robustness of this workflow when facing simulated challenging conditions: (Im) degrades image quality (11-pixel Gaussian blur and 0.5 gamma compression); (4c) uses few cameras (4 vs. 8); and (Cal) introduces calibration errors (1 cm vs. perfect calibration). Three physical activities were investigated: walking, running, and cycling. When averaged over all joint angles, stride-to-stride standard deviations lay between 1.7° and 3.2° for all conditions and tasks, and mean absolute errors (compared to the reference condition—Ref) ranged between 0.35° and 1.6°. For walking, errors in the sagittal plane were: 1.5°, 0.90°, 0.19° for (Im), (4c), and (Cal), respectively. In conclusion, Pose2Sim provides a simple and robust markerless kinematics analysis from a network of calibrated cameras. Full article

(This article belongs to the Special Issue Wearables and Computer Vision for Sports Motion Analysis)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Wearables and Computer Vision for Sports Motion Analysis

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI