Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Dec 9;17(12):2864.
doi: 10.3390/s17122864.

Home Camera-Based Fall Detection System for the Elderly

Koldo de Miguel  1 , Alberto Brunete  2 , Miguel Hernando  3 , Ernesto Gambao  4
Affiliations

Home Camera-Based Fall Detection System for the Elderly

Koldo de Miguel et al. Sensors (Basel). .

Abstract

Falls are the leading cause of injury and death in elderly individuals. Unfortunately, fall detectors are typically based on wearable devices, and the elderly often forget to wear them. In addition, fall detectors based on artificial vision are not yet available on the market. In this paper, we present a new low-cost fall detector for smart homes based on artificial vision algorithms. Our detector combines several algorithms (background subtraction, Kalman filtering and optical flow) as input to a machine learning algorithm with high detection accuracy. Tests conducted on over 50 different fall videos have shown a detection ratio of greater than 96%.

Keywords: camera-based; elderly; fall detection; home automation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Fall detection system prototypes. (a) first prototype; (b) second prototype.
Figure 2
Figure 2
Model diagram.
Figure 3
Figure 3
Example of a fall occurring perpendicular to the camera. (a) ratio; (b) angle; (c) normalized delta of the ratio.
Figure 3
Figure 3
Example of a fall occurring perpendicular to the camera. (a) ratio; (b) angle; (c) normalized delta of the ratio.
Figure 4
Figure 4
Example of fall occurring parallel to the camera. (a) ratio; (b) angle; (c) normalized delta of the ratio.
Figure 4
Figure 4
Example of fall occurring parallel to the camera. (a) ratio; (b) angle; (c) normalized delta of the ratio.
Figure 5
Figure 5
Foreground extraction. (a) original image; (b) extracted foreground. Areas detected as shadows are coloured in grey; (c) final cleaned foreground mask.
Figure 6
Figure 6
Broken contour reconstruction example. (a) image with separated contours; (b) image with reconstructed contour.
Figure 7
Figure 7
Kalman filter predictions for subject position. (a) Step 1: walking; (b) Step 2: fall initiated; (c) Step 3: fall terminated.
Figure 8
Figure 8
Optical flow applied to the subject in a scene. (a) Subject rotating. (b) Subject getting up after a fall event.
Figure 9
Figure 9
Example of an occlusion caused by a desk. (a) subject occluded by a desk; (b) an occluded fall behind a desk.
Figure 10
Figure 10
Fall warning delivery example.
Figure 11
Figure 11
Example of system installation in a home.
See this image and copyright information in PMC

References

    1. World Health Organization . WHO Global Report on Falls Prevention in Older Age. World Health Organization; Geneva, Switzerland: 2007.
    1. Rodrigues R., Rodrigues M., Lamura G. Facts and Figures on Healthy Ageing and Long-Term Care. European Centre for Social Welfare Policy and Research; Viena, Austria: 2012.
    1. Alzheimer’s Disease International (ADI) World Alzheimer Report 2013. Alzheimer’s Disease International (ADI); London, UK: 2013.
    1. World Health Organization and Alzheimer’s Disease International . Dementia: A Public Health Priority. World Health Organization; Geneva, Switzerland: 2012.
    1. Brunete A., Selmes M., Selmes J. Can smart homes extend people with Alzheimer’s disease stay at home? J. Enabling Technol. 2017;11:6–12. doi: 10.1108/JET-12-2015-0039. - DOI