Sistema inteligente usando video cámaras y motion capture para monitoreo de la rehabilitación de la mano derecha

Abstract

Rehabilitation monitoring has become a prominent advancement in the technological field, thanks to the convergence of different technologies. The integration of these technologies allows for more accurate and detailed monitoring of hand rehabilitation gest ures. Through data capture and analysis real time information about the rehabilitation progress is provided, enabling healthcare professionals and users to assess their performance during the process. Moreover, the system not only offers visual tracking of daily progress but also motivates users to continue their treatment, contributing to the success of their rehabilitation. In this research project, various technologies are implemented to facilitate the monitoring and analysis of hand rehabilitation data . Firstly, the Leap Motion Controller is used to capture hand position and direction data during the performed gestures. These data are processed using a custom acquisition system developed in Matlab, enabling their analysis, and generating a dataset. The dataset is preprocessed and relevant features are extracted for the classification of each gesture. For this, different models are implemented, such as Artificial Neural Networks (ANN) and K Nearest Neighbors (KNN) to obtain a high accuracy in the classifi cation. After training, ANN with 93% accuracy was selected. Once the model is trained, it is integrated into Unity, where an interactive interface is created to provide visual feedback to the user, allowing them to perform the gestures effectively and moni tor their progress during rehabilitation.