Multidimensional Measurement of Virtual Human Bodies Acquired with Depth Sensors

• Andrés Fuster-Guilló ^[1] ; Jorge Azorín-López ^[1] ; Juan Miguel Castillo-Zaragoza ^[1] ; Cayetano Manchón-Pernis ^[1] ; Luis Fernando Pérez-Pérez ^[1] ; Ana Zaragoza-Martí ^[1]
  1. [1] Universitat d'Alacant

     Universitat d'Alacant

     Alicante, España

     
• Localización: 15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020): Burgos, Spain ; September 2020 / coord. por Álvaro Herrero Cosío , Carlos Cambra Baseca , Daniel Urda Muñoz , Javier Sedano Franco , Héctor Quintián Pardo , Emilio Santiago Corchado Rodríguez , 2021, ISBN 978-3-030-57802-2, págs. 721-730
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Obtaining 3D measurements of the human body requires precise scanning of the body, as well as methods for extracting these 1D/2D and 3D measurements from the selected volumes. The analysis of these 3D measurements and their monitoring over time (4D) in patients undergoing dietary treatment is a field that poses multidisciplinary challenges such as obtaining precise body models, automating the measurement process and analysing the data from a medical point of view. In this work, we propose a framework to acquire 3D models of patients and obtainmeasurements on these models. This framework incorporates computational methods for extracting 3D models that faithfully represent the human body, as well as methods for obtaining accurate measurements from those 3D models. An analysis of the accuracy of the proposed methods for obtaining measurements with both synthetic and real objects has been carried out. The low level of error observed in the experimentation on synthetic objects allows to attribute most of it to the scanning module. Experiments with real objects and body models show an error level comparable to other scanning systems based on RGB-D technologies. The main contribution of the work is to provide a framework to obtain in a selective and automatic way the 3D measurements of the human body, allowing the analysis of its evolution (4D) during the treatment of obesity.