Print Email Facebook Twitter Feasibility and validity of a single camera CNN driven musculoskeletal model for muscle force estimation during upper extremity strength exercises Title Feasibility and validity of a single camera CNN driven musculoskeletal model for muscle force estimation during upper extremity strength exercises: Proof-of-concept Author Noteboom, L. (Vrije Universiteit Amsterdam) Hoozemans, Marco J.M. (Vrije Universiteit Amsterdam) Veeger, H.E.J. (TU Delft Biomechanical Engineering) van der Helm, F.C.T. (TU Delft Biomechatronics & Human-Machine Control) Department Biomechanical Engineering Date 2022 Abstract Muscle force analysis can be essential for injury risk estimation and performance enhancement in sports like strength training. However, current methods to record muscle forces including electromyography or marker-based measurements combined with a musculoskeletal model are time-consuming and restrict the athlete's natural movement due to equipment attachment. Therefore, the feasibility and validity of a more applicable method, requiring only a single standard camera for the recordings, combined with a deep-learning model and musculoskeletal model is evaluated in the present study during upper-body strength exercises performed by five athletes. Comparison of muscle forces obtained by the single camera driven model against those obtained from a state-of-the art marker-based driven musculoskeletal model revealed strong to excellent correlations and reasonable RMSD's of 0.4–2.1% of the maximum force (Fmax) for prime movers, and weak to strong correlations with RMSD's of 0.4–0.7% Fmax for stabilizing and secondary muscles. In conclusion, a single camera deep-learning driven model is a feasible method for muscle force analysis in a strength training environment, and first validity results show reasonable accuracies, especially for prime mover muscle forces. However, it is evident that future research should investigate this method for a larger sample size and for multiple exercises. Subject artificial intelligencefitnessmarkerless motion capturemusculoskeletal modelingstrength trainingvideo-based motion capture To reference this document use: http://resolver.tudelft.nl/uuid:0b1c5dfa-d24f-4688-b867-54c230c04a23 DOI https://doi.org/10.3389/fspor.2022.994221 Source Frontiers in Sports and Active Living, 4 Part of collection Institutional Repository Document type journal article Rights © 2022 L. Noteboom, Marco J.M. Hoozemans, H.E.J. Veeger, F.C.T. van der Helm Files PDF fspor_04_994221.pdf 2.19 MB Close viewer /islandora/object/uuid:0b1c5dfa-d24f-4688-b867-54c230c04a23/datastream/OBJ/view