Leandro Abraham1, Facundo Bromberg2, Raymundo Forradellas3. 1. Laboratorio DHARMa, DeSI, Universidad Tecnológica Nacional, Facultad Regional Mendoza - Rodriguez 273, PC M5502AJE Mendoza, Argentina; CEAL, Universidad Nacional de Cuyo, Facultad de Ingeniería - Centro Universitario CC 405, PC M5500AAT Mendoza, Argentina; Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Argentina. Electronic address: leandro.abraham@frm.utn.edu.ar. 2. Laboratorio DHARMa, DeSI, Universidad Tecnológica Nacional, Facultad Regional Mendoza - Rodriguez 273, PC M5502AJE Mendoza, Argentina; Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Argentina. Electronic address: fbromberg@frm.utn.edu.ar. 3. CEAL, Universidad Nacional de Cuyo, Facultad de Ingeniería - Centro Universitario CC 405, PC M5500AAT Mendoza, Argentina. Electronic address: kike@uncu.edu.ar.
Abstract
BACKGROUND: Muscle activation level is currently being captured using impractical and expensive devices which make their use in telemedicine settings extremely difficult. To address this issue, a prototype is presented of a non-invasive, easy-to-install system for the estimation of a discrete level of muscle activation of the biceps muscle from 3D point clouds captured with RGB-D cameras. METHODS: A methodology is proposed that uses the ensemble of shape functions point cloud descriptor for the geometric characterization of 3D point clouds, together with support vector machines to learn a classifier that, based on this geometric characterization for some points of view of the biceps, provides a model for the estimation of muscle activation for all neighboring points of view. This results in a classifier that is robust to small perturbations in the point of view of the capturing device, greatly simplifying the installation process for end-users. RESULTS: In the discrimination of five levels of effort with values up to the maximum voluntary contraction (MVC) of the biceps muscle (3800 g), the best variant of the proposed methodology achieved mean absolute errors of about 9.21% MVC - an acceptable performance for telemedicine settings where the electric measurement of muscle activation is impractical. CONCLUSIONS: The results prove that the correlations between the external geometry of the arm and biceps muscle activation are strong enough to consider computer vision and supervised learning an alternative with great potential for practical applications in tele-physiotherapy.
BACKGROUND: Muscle activation level is currently being captured using impractical and expensive devices which make their use in telemedicine settings extremely difficult. To address this issue, a prototype is presented of a non-invasive, easy-to-install system for the estimation of a discrete level of muscle activation of the biceps muscle from 3D point clouds captured with RGB-D cameras. METHODS: A methodology is proposed that uses the ensemble of shape functions point cloud descriptor for the geometric characterization of 3D point clouds, together with support vector machines to learn a classifier that, based on this geometric characterization for some points of view of the biceps, provides a model for the estimation of muscle activation for all neighboring points of view. This results in a classifier that is robust to small perturbations in the point of view of the capturing device, greatly simplifying the installation process for end-users. RESULTS: In the discrimination of five levels of effort with values up to the maximum voluntary contraction (MVC) of the biceps muscle (3800 g), the best variant of the proposed methodology achieved mean absolute errors of about 9.21% MVC - an acceptable performance for telemedicine settings where the electric measurement of muscle activation is impractical. CONCLUSIONS: The results prove that the correlations between the external geometry of the arm and biceps muscle activation are strong enough to consider computer vision and supervised learning an alternative with great potential for practical applications in tele-physiotherapy.
Authors: Vito M Manghisi; Michele Fiorentino; Antonio Boccaccio; Michele Gattullo; Giuseppe L Cascella; Nicola Toschi; Antonio Pietroiusti; Antonio E Uva Journal: Sensors (Basel) Date: 2020-10-29 Impact factor: 3.576