The quest for personalized sports therapy has long been a concern for practitioners and patients alike aiming for recovery protocols that transcend the one-size-fits-all approach. In this study we introduce a novel framework for personalized sports therapy through automated joint movement analysis. By synthesizing the analytical capabilities of a Random Forest Classifier (RFC) with a Vector Quantized Variational AutoEncoder (VQ-VAE) we systematically discern the nuanced kinematic differences between healthy and pathological exercise movements. The RFC prioritizes the joints by their discriminative influence on movement healthiness which informs the VQ-VAE's derivation of a distilled list of pivotal joints. This dual-model approach not only identifies a hierarchy of joint importance but also ascertains the minimal subset of joints critical for distinguishing between healthy and unhealthy movement patterns. The resultant data-driven insight into joint-specific dynamics underpins the development of targeted individualized rehabilitation programs. Our results exhibit promising directions in sports therapy showcasing the potential of machine learning in developing personalized therapeutic interventions. ExerAIde: KI-unterstützte multimodale Diagnose für verbesserte sportliche Leistung und personalisierte Rehabilitation
© Copyright 2024 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. Veröffentlicht von IEEE. Alle Rechte vorbehalten.