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
. 2012;12(1):573-84.
doi: 10.3390/s120100573. Epub 2012 Jan 5.

Visual sensor based abnormal event detection with moving shadow removal in home healthcare applications

Young-Sook Lee  1 , Wan-Young Chung
Affiliations

Visual sensor based abnormal event detection with moving shadow removal in home healthcare applications

Young-Sook Lee et al. Sensors (Basel). 2012.

Abstract

Vision-based abnormal event detection for home healthcare systems can be greatly improved using visual sensor-based techniques able to detect, track and recognize objects in the scene. However, in moving object detection and tracking processes, moving cast shadows can be misclassified as part of objects or moving objects. Shadow removal is an essential step for developing video surveillance systems. The goal of the primary is to design novel computer vision techniques that can extract objects more accurately and discriminate between abnormal and normal activities. To improve the accuracy of object detection and tracking, our proposed shadow removal algorithm is employed. Abnormal event detection based on visual sensor by using shape features variation and 3-D trajectory is presented to overcome the low fall detection rate. The experimental results showed that the success rate of detecting abnormal events was 97% with a false positive rate of 2%. Our proposed algorithm can allow distinguishing diverse fall activities such as forward falls, backward falls, and falling asides from normal activities.

Keywords: abnormal event detection; shape features variation, shadow removal algorithm; ubiquitous healthcare surveillance; visual sensor.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
Segmentation results for image sequence “intelligent room”: (a) Original images; (b) Segmentation results with FSD using our shadow removal algorithm; (c) Segmentation results with FSD and SSD using our shadow removal algorithm; (d) Results of object detection.
Figure 2.
Figure 2.
Results of abnormal event detection: (a) Original image; (b) Depth image corresponding to (a); (c) Result with UFED1 (not detected); (d) Result with a combination of UFED1 and UFED2 (detected).
Figure 3.
Figure 3.
Variations in the MBR ratio: (a) Backward fall; (b) Forward fall; (c) Falling to the left; (d) Falling to the right; (e) Crouching down and standing up; (f) Standing; (g) Walking.
Figure 4.
Figure 4.
Variations of 2-D vertical velocity during different human activities: (a) Backward fall; (b) Forward fall; (c) Falling to the left; (d) Falling to the right; (e) Crouching down and standing up; (f) Standing; (g) Walking.
Figure 5.
Figure 5.
Variations of 3-D centroids for the example shown in Figure 2 during different human activities: (a) Walking; (b) Standing; (c) Backward fall.
See this image and copyright information in PMC

References

    1. Challenges of Global Aging. U.S. Department of Health and Human Services; Available online: http://www.aoa.gov/ (accessed on 10 September 2011).
    1. Hitcho E.B., Krauss M.J., Birge S., Dunagan W.C., Fischer I., Johnson S., Nast P.A., Costantinou E., Fraser V.J. Characteristics and circumstances of falls in a hospital setting: A prospective analysis. J. Gen. Intern. Med. 2004;19:732–739. - PMC - PubMed
    1. Tinetti M.E., Baker D.I., Dutcher J., Vincent J.E., Rozett R.T. Reducing the Risk of Falls among Older Adults in the Community. Peaceable Kingdom Press; Berkeley, CA, USA: 1997.
    1. Alwan M., Rajendran P.J., Kell S., Mack D., Dalal S., Wolfe M., Felde R. A smart and passive floor-vibration based fall detector for elderly. Proceedings of ICTTA '06: Information and Communication Technologies; Damascus, Syria. 24–28 April 2006; pp. 1003–1007.
    1. Purwar A., Jeong D.U., Chung W.Y. Activity monitoring from real-time triaxial accelerometer data using sensor network. Proceedings of ICCAS 2007: International Conference on Control, Automation and Systems; Seoul, Korea. 17–20 October 2007; pp. 2402–2406.

Publication types