Contactless Body Measurement System Using Single Fixed-Point RGBD Camera Based on Pose Graph Reconstruction

• Published in: IEEE access 2024, Vol.12, p.84363-84373
• Main Authors: Cherdchusakulchai, Riu, Thoumrungroje, Sucharn, Tungpanjasil, Thanyaporn, Pimpin, Alongkorn, Srituravanich, Werayut, Damrongplasit, Nattapol
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Anthropometry; Atmospheric measurements; Body measurements; Cameras; depth camera; Error analysis; Human bias; Human body; human body measurement; human body segmentation; Image reconstruction; Measurement methods; Particle measurements; Physicians; Point cloud compression; point cloud reconstruction; pose graph; Reconstruction; RGBD camera; skeleton tracking; Three-dimensional displays
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3414658

Accurate anthropometric measurements are critical in the healthcare industry for effective diagnosis and patient monitoring. Standardized procedures for measuring human body dimensions are required to ensure accuracy, reliability, and consistency across measurement data. Traditional body measurement administered by trained physicians is susceptible to human bias and often requires direct physical contact with the patient which can be intrusive. Other measurement systems have been introduced to automate the process and reduce reliance on physicians, but they tend to be expensive and complicated to set up and operate. This study aims to develop a cost-effective method for measuring anthropometric parameters using a single RGBD camera designed for easy deployment and low computing resources. The system only requires the participant to rotate a full 360-degree in front of the camera to reconstruct a detailed 3D human body model based on pose graph reconstruction. A study involving 20 participants is conducted to evaluate the accuracy of the proposed system as compared to traditional measurement using a tape measure. The result shows a height percentage error of 0.55 %, while hip and waist measurements show an error of 3.84 % and 6.90 %, respectively. The integration of the ellipse shrinkage method into the algorithm effectively improves hip and waist measurements by minimizing the impact of clothing.