Deep learning for anthropometry with smart devices

Project Member(s): Ha, Q.

Funding or Partner Organisation: The Darwin Practice Pty Ltd
The Darwin Practice Pty Ltd

Start year: 2020

Summary: The existing Civilian American and European Surface Anthropometry Resource (CAESAR) model is adopted at SmartFit Technologies as anthropometric indicators for a generic population, which include means, standard deviations and percentiles. However, for engineering applications this information is generally not suitable nor sufficient, considering for example the demographic mix or a particular age group. As such, the measurement of interest for a design may be different from the CAESAR model. This prompts for potential improvements, e.g. from advanced techniques in image processing or machine learning. The main objective of this project is to increase accuracy of measurement model so that 95% of the cases has less than 10mm error across all body measurements.

FOR Codes: Information Services not elsewhere classified, Control Systems, Robotics and Automation, Control engineering, mechatronics and robotics, Information services

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.