Automating senior fitness testing through gesture detection with depth sensors

Sedentarism has a negative impact on health, life expectancy and quality of life, especially in older adults. According to current projections, nearly one third of European citizens will be aged 65 or over by 2060. In addition to these demographic changes, sedentarism is the 4th main factor in worldwide mortality, being associated with 21- 25% of breast and colon cancer cases, 27% of diabetes, and 30% of ischemic strokes. The combination of ageing with sedentary behaviours is a growing concern, and is putting a high strain on modern societies and their health systems. There is strong scientific evidence that regular (moderate-tovigorous intensity) physical activity produces major and extensive health benefits in adults, particularly in older adults (aged 65 and above), as they suffer more frequently the consequences of inactivity.

In older adults, the assessment of multiple dimensions of physical function is commonly done using Senior Fitness Tests (SFT). These tests assess several physical parameters such as muscle strength, agility and dynamic balance, and aerobic endurance. We developed 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.

Reference:

Gonçalves, A. R., Gouveia, E. R., Cameirão, M. S., & Bermúdez i Badia, S. (2015). Automating Senior Fitness Testing Through Gesture Detection with Depth Sensors. In IET International Conference on Technologies for Active and Assisted Living (TechAAL 2015). INSPEC, IEEE. (Download) (Cite)