Abstract
Falls occurring at home are a high risk for elderly living alone. Several sensor-based methods for detecting falls exist and – in majority – use wearables or ambient sensors. Video-based fall detection is emerging. However, the restricted view of a single camera, distinguishing and tracking of persons, as well as high false-positive rates pose limitations.
Contributor Information
Christoph Palm, Email: christoph.palm@oth-regensburg.de.
Thomas M. Deserno, Email: thomas.deserno@plri.de
Heinz Handels, Email: handels@imi.uni-luebeck.de.
Andreas Maier, Email: duplicateandreas.maier@fau.de.
Klaus Maier-Hein, Email: k.maier-hein@dkfz-heidelberg.de.
Thomas Tolxdorff, Email: thomas.tolxdorff@charite.de.
Christian Heinrich, Email: christian.heinrich@plri.de.
References
- 1.Taufeeque M, Koita S, Spicher N, et al. Multi-camera, multi-person, and real-time fall detection using long short term memory. Proc SPIE. 2021;Accepted.