ReBase: a framework for acquiring and managing body tracking data

• Autor(a) principal: Trotta, Tiago
• Data de Publicação: 2024
• Outros Autores: Rodrigues, Luis [UNESP], Brega, José Remo [UNESP], Guimarães, Marcelo, Rocha, Leonardo, Brandão, Alexandre, Dias, Diego
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1145/3691573.3691578; https://hdl.handle.net/11449/305446
• topic: Augmented reality; Database; Framework; Machine learning; Neurorehabilitation; Virtual reality

There is a great deal of interest in developing virtual reality and augmented reality applications that require data storage, with which developers can interact and create intelligent systems for various purposes, such as applications for neuromotor rehabilitation. These applications provide the benefits of traditional rehabilitation without becoming overwhelming, as they allow the user to be immersed in various scenarios and situations. In addition, the way these applications interact makes it possible to retrieve and analyze the data generated by users’ movements during treatment. However, it is tough to find datasets of body movements, and those that do exist do not include movements specific to the rehabilitation context. This paper, therefore, presents ReBase, a framework that provides a standardized storage system for body movement data. ReBase was designed to allow the collection of data generated by any application, regardless of the form of body tracking used. This paper presents an open API that can be used to communicate with the ReBase database, a package for the Unity game engine, and a library for the Python programming language, which facilitates the integration of new applications into the system. In addition, two applications are shown as case studies within and outside the health area, developed using the tool.