Generating a novel synthetic dataset for rehabilitation exercises using pose-guided conditioned diffusion models: A quantitative and qualitative evaluation

• Published in: Computers in biology and medicine Vol. 167; p. 107665
• Main Authors: Mennella, Ciro, Maniscalco, Umberto, De Pietro, Giuseppe, Esposito, Massimo
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.12.2023; Elsevier Limited
• Subjects: Aged; Artificial Intelligence; Biomechanics; Computer vision; Consistency; Datasets; Deep learning; Diffusion models; Exercise; Exercise Therapy - methods; Generative models; Human motion; Humans; Image enhancement; Image processing; Internal Medicine; Learning algorithms; Machine Learning; Movement; Other; Pose estimation; Rehabilitation; Synthetic data; Deep learning; Computer vision; Rehabilitation; Generative models; Pose estimation; Artificial Intelligence

Machine learning has emerged as a promising approach to enhance rehabilitation therapy monitoring and evaluation, providing personalized insights. However, the scarcity of data remains a significant challenge in developing robust machine learning models for rehabilitation. This paper introduces a no...