Validation of Angle Estimation Based on Body Tracking Data from RGB-D and RGB Cameras for Biomechanical Assessment

• DOI: 10.3390/s23010003
• Publication Date: 2022-12-20T08:29:20Z
• Authors: Thiago Buarque de...; Victor Hugo de Li...; Pedro Vanderlei d...; Paulo de Oliveira...; João Marcelo Xavi...; Cínthia Rodrigues...; Veronica Teichrieb; Alana Elza Fontes...
• Keywords: RGB color model; Goniometer; Tracking (education); Match moving

Motion analysis is an area with several applications for health, sports, and entertainment. The high cost of state-of-the-art equipment in the health field makes it unfeasible to apply this technique clinics’ routines. In vein, RGB-D RGB equipment, which have joint tracking tools, are tested portable low-cost solutions enable computational motion analysis. recent release Google MediaPipe, a inference that uses conventional cameras, can be considered milestone due its ability estimate depth coordinates planar images. light this, work aims evaluate measurement angular variation from sensor data against Qualisys Tracking Manager gold standard. A total 60 recordings were performed each upper lower limb movement two different position configurations concerning sensors. Google’s MediaPipe usage obtained close results compared Kinect V2 inherent aspects absolute error, RMS, correlation standard, presenting dispersion values error metrics, more positive. comparison commonly used physical evaluations, had within range short- long-arm goniometers.