ResearchAssistive living & remote care

Fall Detection

Automatic fall detection from wearable motion, sound and fisheye-camera video, with fewer false alarms.

Falls are a leading cause of injury among older adults, and the speed of response matters. We develop systems that detect falls automatically and raise an alarm without requiring the person to press a button.

We combine complementary sources: motion data from wearable and hand-held devices, sound, and video from ceiling-mounted fisheye cameras. Filtering and rule-based evaluation reduce false alarms, while recent work achieves real-time detection with uncalibrated fisheye cameras.

Wearable and smartphone motion sensing
Sound and visual data fusion
Real-time fisheye-camera detection

Related publications

Selected work from the lab in this area.

2022

Hardware/Software Co-Design of a Low-Power IoT Fall Detection Device

Karagiannis, D., Maglogiannis, I., Nikita, K.S. and Tsanakas, P. (2022)

In Internet of Things. Technology and Applications. Springer International Publishing, pp. 146–159.

DOI

2020

Real-Time Fall Detection Using Uncalibrated Fisheye Cameras

Kottari, K.N., Delibasis, K.K. and Maglogiannis, I.G. (2020)

IEEE Transactions on Cognitive and Developmental Systems, 12(3), pp. 588–600.

DOI

2019

Deep Learning and Change Detection for Fall Recognition

Tasoulis, S.K., Mallis, G.I., Georgakopoulos, S.V., Vrahatis, A.G., Plagianakos, V.P. and Maglogiannis, I.G. (2019)

In Engineering Applications of Neural Networks. Springer International Publishing, pp. 262–273.

DOI

2016

Fall detection and activity identification using wearable and hand-held devices

Maglogiannis, I., Ioannou, C. and Tsanakas, P. (2016)

Integrated Computer-Aided Engineering, 23(2), pp. 161–172.

DOI

2015

On-Line Fall Detection via Mobile Accelerometer Data

Georgakopoulos, S.V., Tasoulis, S.K., Maglogiannis, I. and Plagianakos, V.P. (2015)

In Artificial Intelligence Applications and Innovations. Springer International Publishing, pp. 103–112.

DOI

2014

Fall Detection Using Commodity Smart Watch and Smart Phone

Maglogiannis, I., Ioannou, C., Spyroglou, G. and Tsanakas, P. (2014)

In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Springer International Publishing, pp. 70–78.

DOI

2013

Statistical data mining of streaming motion data for activity and fall recognition in assistive environments

Tasoulis, S.K., Doukas, C.N., Plagianakos, V.P. and Maglogiannis, I. (2013)

Neurocomputing, 107, pp. 87–96.

DOI

2011

Emergency Fall Incidents Detection in Assisted Living Environments Utilizing Motion, Sound, and Visual Perceptual Components

Doukas, C.N. and Maglogiannis, I. (2011)

IEEE Transactions on Information Technology in Biomedicine, 15(2), pp. 277–289.

DOI

2010

An assistive environment for improving human safety utilizing advanced sound and motion data classification

Doukas, C. and Maglogiannis, I. (2010)

Universal Access in the Information Society, 10(2), pp. 217–228.

DOI

2010

Open Research Issues in Vision-Based Fall Detection Systems (FDS)

Kolovou, X., Doukas, C., Vergados, D., Anagnostopoulos, I. and Maglogiannis, I. (2010)

In Proceedings of the 7th European Symposium on Biomedical Engineering (ESBME 2010). Greece.

2010

Advanced Classification and Rules-Based Evaluation of Motion, Visual and Biosignal Data for Patient Fall Incident Detection

Doukas, C. and Maglogiannis, I. (2010)

International Journal on Artificial Intelligence Tools, 19(02), pp. 175–191.

DOI

2011

Statistical data mining of streaming motion data for fall detection in assistive environments

Tasoulis, S.K., Doukas, C.N., Maglogiannis, I. and Plagianakos, V.P. (2011)

In 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, pp. 3720–3723.

DOI

Browse all publications