ECSS Paris 2023: OP-AP30
INTRODUCTION: Analyzing muscle force during weightlifting is a crucial indicator for injury prevention and performance enhancement, and understanding individual muscle forces can prevent overloading and provide optimal training stimuli [1]. Marker-based methods using optoelectronic motion capture systems (OMS) and inertial measurement units (IMU) are primarily utilized for analyzing muscle loads. However, these methods have limitations such as the requirement for spacious laboratory environments with equipment, as well as time-consuming experimental setups and analysis [2]. Therefore, marker-free 3D human pose estimation (HPE) using deep learning is advantageous for application in actual environments since it requires only one camera. METHODS: In this study, one healthy male (28years, 173cm, 73kg) performed deep squat for 3 set of 5 repetitions. Marker trajectories during deep squat were obtained through a OMS (Vicon Motion Systems), and simultaneously, a 2D camera was used for marker-less HPE analysis. Jointformer model [3], which was pre-trained on the H3WB dataset [4], has been used to transform 2D camera data into 3D coordinates. Lower limb muscle force (Gluteus maximus, gluteus medialis, rectus femoris, vastus lateralis, vastus intermedius vastus medialis) were calculated and compared using coordinates obtained through OMS and HPE, employing Opensim full-body squat model. RESULTS: As a result, the muscle force of OMS was observed to be 355N in gluteus maximus, 91N in gluteus medialis, 399N in rectus femoris, 150N in vastus intermedius, 78N in vastus lateralis, 237N in vastus medialis, respectively. In addition, the muscle force of HPE is analyzed after the predicted 3D coordinates, and the root mean squared error (RMSE) between the ground truth coordinates measured by 3D markers (OMS) and the predicted 2D-3D coordinates using the Jointformer showed a slight difference. CONCLUSION: The proposed method analyzed muscle force using marker-less techniques, enabling immediate provision of safety guidelines and methods for training in the sports field. Moreover, it will serve as a foundation for developing models applicable for real-time analysis using 2D single cameras in future research. REFERENCES: 1. Kemler E, Noteboom L, Beijsterveldt A. (2022). Injuries sustained during fitness activities in the Netherlands: results of a retrospective study. 2. Van der Kruk, E., & Reijne, M. M. (2018). Accuracy of human motion capture systems for sport applications; state-of-the-art review. Eur J Sport Sci, 18(6), 806-819. 3. Zhu, Y., Samet, N., & Picard, D. (2023). H3wb: Human3. 6m 3d wholebody dataset and benchmark. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 20166-20177). 4. Lutz, S., Blythman, R., Ghosal, K., Moynihan, M., Simms, C., & Smolic, A. (2022, August). Jointformer: Single-frame lifting transformer with error prediction and refinement for 3d human pose estimation. In 2022 26th International Conference on Pattern Recognition (ICPR) (pp. 1156-1163). IEEE.
Read CV Yun-Hwan LeeECSS Paris 2023: OP-AP30
INTRODUCTION: Heart rate variability (HRV) and psychological assessments are used to monitor the athlete’s response to training and their subsequent recovery status. However, the relationship between HRV and perceptions is not yet understood. The purpose of this cross-sectional study was to explore the associations between HRV and subjective measures of fatigue, recovery, and psychological state. METHODS: Twenty-five competitive endurance athletes (20.6 ± 2.06 yrs.) were examined in the morning (08:00 to 12:00) after a training session (>6 Rating of Perceived Exertion, > 60 minutes). Heart rate variability (lnRMSSD, pNN50) was determined through 5-minute electrocardiogram recording. The psychological assessments which indicate perceived recovery status were the Total Quality Recovery scale, Perceived Recovery Status scale, Hooper Index and Total Mood Disturbance Score. Pearson’s Correlation Coefficient was used to assess the associations between HRV and each of the four psychological assessments. Mean HRV was compared between athletes, when grouped according to recovery status, via the Total Quality Recovery (≥13 or <13) and Perceived Recovery Status (>5 or <5) scales. RESULTS: A low positive correlation was found between the Total Quality Recovery score and lnRMSSD (r = 0.435, 95% CI = 0.048 – 0.708). Non-significant correlations were reported for all other relationships. A significant mean difference in lnRMSSD and pNN50 was found between athletes with different recovery states on both the Total Quality Recovery (MD = 0.7, 95% CI= 0.17 – 1.22; MD = 23.33, 95% CI= 4.46 - 42.19) and Perceived Recovery Status (MD=0.71, 95% CI= 0.21-1.22; MD = 23.99, 95% CI= 5.66 - 42.34) scales. CONCLUSION: Our findings suggest that there is a limited association between HRV and perceived recovery scores in endurance athletes. When grouped by recovery status, athletes exhibit differences in HRV. This study warrants further exploration of the relationship between HRV and subjective perceptions of fatigue.
Read CV Peter HigginsECSS Paris 2023: OP-AP30
INTRODUCTION: The 30-second Wingate anaerobic test (WAnT30) is commonly used to assess an individual’s capacity to generate power from anaerobic energy systems in a laboratory [1]. Whilst the WAnT30 has been shown to be valid and reliable [2], criticisms and limitations are apparent [3]. The use of modified Wingate anaerobic tests (WAnT) comprising 6-, 10-, or 20-second protocols have been proposed as more effective alternatives to the WAnT30 where peak power (PP) is the measure of interest [1,2,4]. Moreover, anaerobic test accessibility has improved with the development of commercially available Wattbikes that integrate a cycling ergometer with user-friendly software. The primary objective of this study was to assess criterion validity of the Wattbike Pro to measure PP. Comparisons were made between a 6-second test on the Wattbike Pro (PPT6) and the WAnT6 and WAnT30 tests performed on a laboratory ergometer. Where systematic bias was encountered, a second objective of the study was to quantify uncertainty in standard correction equations. METHODS: Thirty-five participants (males: n=30, 21.3 ± 1.6 yrs, 182.3 ± 8.4 cm, 83.9 ± 12.2 kg; Females: n=5, 23.1 ± 2.2 yrs, 168.5 ± 4.8 cm, 69.1. ± 4.8kg) completed two testing sessions in a randomised order on separate days. One testing session included the WAnT30 and the other included the PPT6 and WAnT6 performed in a random order. A Bayesian framework was used to compare group means and to conduct Bland-Altman analyses to assess criterion validity. Bayes factor (BF) with qualitative interpretation of strength of evidence was used to interpret difference in group means. Stability of correction equations were assessed by quantifying uncertainty in regression parameters and fitted values when regressing WAnT6 and WAnT30 on PPT6. RESULTS: Comparison of WAnT30 and WAnT6 identified “extreme evidence” for greater PP produced during WAnT6 (Difference0.5 = 33.9 [95%CrI: 10.2 to 57.8 W]; BF>100). Bland-Altman analyses identified similar overestimations for PPT6 relative to both WAnT6 and WAnT30. No heteroscedasticity was observed, but proportional biases with overestimations of ~115 W for those at the 0.25-quantile and ~200 W for those at the 0.75-quantile were found. Substantive uncertainty was identified in regression parameters of correction equations corresponding to plausible changes of up to ~60 to 80 W in fitted values. CONCLUSION: The findings suggest that where PP is of primary interest the WAnT6 should be performed. Where there is no access to a laboratory ergometer, PPT6 can be an appropriate substitute. However, comparing PPT6 with WAnT values, or attempting to predict WAnT values should be used with caution.
Read CV Rodrigo AspeECSS Paris 2023: OP-AP30