Depth-Based Fall Detection: Outcomes from a Real Life Pilot
With the increasing ageing population representing a challenge for society and health care systems, solutions based on ICT to prolong the independent living of older adults become critical. Among them, systems able to automatically detect falls are being investigated since several years, because many solutions that appear promising when tested in lab settings, fail when faced with the constraints and unforeseen circumstances of real deployments. In this paper, we present the outcomes resulting from the pilot installation of a fall detection system based on the use of depth sensors located on the ceiling of the monitored apartment, where a 75 years old woman lives alone. We highlight the system design process, moving from the research leading to an original algorithm working offline, preliminarily tested in a lab setting, to the real-time engineering of the software, and the physical deployment of the system. Testing the system in a real-life scenario allowed us to identify a number of tricks and conditions that should to be taken into account since the initial steps, but the lab experimentation alone can barely help to focus on.
KeywordFall detection Depth sensor Machine learning
- 1.AAL Joint Platform: ICT for ageing well. http://www.aal-europe.eu/about/why-thisprogramme/
- 4.World Health Organization. Falls: fact sheet. http://www.who.int/en/newsroom/fact-sheets/detail/falls. Accessed on May 3rd, 2018
- 6.Turner S, Kisser R, Rogmans W (2015) Falls among older adults in the EU-28: key facts from the available statistics. EuroSafe, AmsterdamGoogle Scholar
- 11.Kit Intel NUC NUC7i3BNH. https://www.intel.it/content/www/it/it/products/boardskits/nuc/kits/nuc7i3bnh.html