Automating senior fitness testing through gesture detection with depth sensors

• Main Author: Gonçalves, A. R.
• Publication Date: 2015
• Other Authors: Cameirão, M. S., Bermúdez i Badia, S., Gouveia, E. R.
• Language: eng
• Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Download full: http://hdl.handle.net/10400.13/4599
• topic: Senior fitness test; Older adults; Assistive technology; Gesture detection; Kinect; .; Faculdade de Ciências Exatas e da Engenharia

Sedentarism has a negative impact on health, life expectancy and quality of life, especially in older adults. The assessment of functional fitness helps evaluating the effects of ageing and sedentarism, and this assessment is typically done through validated battery tests such as the Senior Fitness Test (SFT). In this paper we present a computer-based system for assisting and automating SFT administration and scoring in the elderly population. Our system assesses lower body strength, agility and dynamic balance, and aerobic endurance making use of a depth sensor for body tracking and multiple gesture detectors for the evaluation of movement execution. The system was developed and trained with optimal data collected in laboratory conditions and its performance was evaluated in a real environment with 22 elderly end-users, and compared to traditional SFT administered by an expert. Results show a high accuracy of our system in identifying movement patterns (>95%) and consistency with the traditional fitness assessment method. Our results suggest that this technology is a viable low cost option to assist in the fitness assessment of elderly that could be deployed for at home use in the context of fitness programs.