IMU Airtime Detection in Snowboard Halfpipe: U-Net Deep Learning Approach Outperforms Traditional Threshold Algorithms
Sensors · 22.10.2024 · 24 (21) · 6773
DOI: 10.3390/s24216773 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.10.2024. Verfasst von Tom Gorges und 4 weiteren Autor:innen. Beteiligte Einrichtung: Research Group Snowboard, Department Strength, Power and Technical Sports, Institute for Applied Training Science, 04109 Leipzig, Germany. Hauptthemen laut MEDLINE: Deep Learning, Algorithms. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Airtime is crucial for high-rotation tricks in snowboard halfpipe performance, significantly impacting trick difficulty, the primary judging criterion. This study aims to enhance the detection of take-off and landing events using inertial measurement unit (IMU) data in conjunction with machine learning algorithms since manual video-based methods are too time-consuming. Eight elite German National Team snowboarders performed 626 halfpipe tricks, recorded by two IMUs at the lateral lower legs and a video camera. The IMU data, synchronized with video, were labeled manually and segmented for analysis. Utilizing a 1D U-Net convolutional neural network (CNN), we achieved superior performance in all of our experiments, establishing new benchmarks for this binary segmentation task. In our extensive experiments, we achieved an 80.34% lower mean Hausdorff distance for unseen runs compared with the threshold approach when placed solely on the left lower leg. Using both left and right IMUs further improved performance (83.37% lower mean Hausdorff). For data from an algorithm-unknown athlete (Zero-Shot segmentation), the U-Net outperformed the threshold algorithm by 67.58%, and fine-tuning on athlete-specific (Few-Shot segmentation) runs improved the lower mean Hausdorff to 78.68%. The fine-tuned model detected takeoffs with median deviations of 0.008 s (IQR 0.030 s), landing deviations of 0.005 s (IQR 0.020 s), and airtime deviations of 0.000 s (IQR 0.027 s). These advancements facilitate real-time feedback and detailed biomechanical analysis, enhancing performance and trick execution, particularly during critical events, such as take-off and landing, where precise time-domain localization is crucial for providing accurate feedback to coaches and athletes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research Group Snowboard, Department Strength, Power and Technical Sports, Institute for Applied Training Science, 04109 Leipzig, Germany.
- Chair for Data Science, Center for Artificial Intelligence and Data Science, University of Würzburg, 97074 Wuerzburg, Germany.
- Institute of Biomechanics and Orthopaedics, German Sport University, 50933 Cologne, Germany.
ORCID-Profile: Tom Gorges, Padraig Davidson, Myriam Boeschen, Andreas Hotho, Christian Merz
Zitieren
APA
Gorges, T., Davidson, P., Boeschen, M., Hotho, A., & Merz, C. (2024). IMU Airtime Detection in Snowboard Halfpipe: U-Net Deep Learning Approach Outperforms Traditional Threshold Algorithms. Sensors, 24(21), 6773. https://doi.org/10.3390/s24216773
Vancouver
Gorges T, Davidson P, Boeschen M, Hotho A, Merz C. IMU Airtime Detection in Snowboard Halfpipe: U-Net Deep Learning Approach Outperforms Traditional Threshold Algorithms. Sensors. 2024;24(21):6773. doi:10.3390/s24216773
BibTeX
@article{Gorges2024,
author = {Gorges, Tom and Davidson, Padraig and Boeschen, Myriam and Hotho, Andreas and Merz, Christian},
title = {IMU Airtime Detection in Snowboard Halfpipe: U-Net Deep Learning Approach Outperforms Traditional Threshold Algorithms},
journal = {Sensors},
year = {2024},
volume = {24},
number = {21},
pages = {6773},
doi = {10.3390/s24216773}
}
EUVIMED