Micro Doppler Radar and Depth Sensor Fusion for Human Activity Monitoring in AAL
Among the older adults population, falls represent a serious health problem, and a considerable economic issue for the society as a whole, due to their many consequences. In order to design reliable systems for automatic fall detection, able to distinguish falls from activities of daily living, the sensor fusion approach may be exploited. In this paper, the quite innovative fusion of Micro Doppler Radar and Kinect sensors to achieve acceptable accuracy and sensitivity in fall detection is investigated. The results show that by fusion, it is possible to provide a 100% fall detection sensitivity, over a dataset collected by taking into account ten different actions, with proper configuration of the acquisition setup and algorithmic parameters.
KeywordsFall detection Sensor fusion Depth Micro doppler radar
M. Pepa was partially supported by COST Action IC1303 under the Short Term Scientific Mission ECOST-STSM-IC1303-200317-084684.
- 1.World Health Organization: falls—fact sheet (2016). http://www.who.int/mediacentre/factsheets/fs344/en/ (last accessed: April 29th, 2018)
- 3.Daponte, P., De Marco, J., De Vito, L., Pavic, B., Zolli, S.: Electronic measurements in rehabilitation. In: 2011 IEEE International Symposium on Medical Measurements and Applications, pp. 274–279, May 2011Google Scholar
- 4.Garcia, N.M., Garcia, N.C., Sousa, P., Oliveira, D., Alexandre, C., Felizardo, V.: TICE.Healthy: A perspective on medical information integration. In: 2014 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2014, art. no. 6864403, pp. 464–467 (2014)Google Scholar
- 5.Martín Martín, R., Lorbach, M., Brock, O.: Deterioration of depth measurements due to interference of multiple RGB-D sensors. In: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, Chicago, IL, pp. 4205–4212 (2014)Google Scholar
- 7.Li, H., Shrestha, A., Fioranelli, F., Le Kernec, J., Heidari, H., Pepa, M., Cippitelli, E., Gambi, E., Spinsante, S.: Multisensor data fusion for human activities classification and fall detection. In: 2017 IEEE Sensors Proceedings, Glasgow, UK, pp. 1–3 (2017)Google Scholar
- 11.Cippitelli, E., Gambi, E., Spinsante, S., Florez-Revuelta, F.: Evaluation of a skeleton-based method for human activity recognition on a large-scale RGB-D dataset. In: 2nd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2016), London, UK, pp. 1–6 (2016)Google Scholar
- 12.Cippitelli, E., Gambi, E., Spinsante, S., Florez-Revuelta, F.: Human action recognition based on temporal pyramid of key poses using RGB-D sensors. In: Blanc-Talon J., Distante C., Philips W., Popescu D., Scheunders P. (eds.) Advanced Concepts for Intelligent Vision Systems. ACIVS 2016. Lecture Notes in Computer Science, vol. 10016. Springer, Cham (2016)CrossRefGoogle Scholar