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 Dec 7;12(12):16920-36.
doi: 10.3390/s121216920.

Privacy-preserved behavior analysis and fall detection by an infrared ceiling sensor network

Shuai Tao  1 , Mineichi Kudo, Hidetoshi Nonaka
Affiliations

Privacy-preserved behavior analysis and fall detection by an infrared ceiling sensor network

Shuai Tao et al. Sensors (Basel). .

Abstract

An infrared ceiling sensor network system is reported in this study to realize behavior analysis and fall detection of a single person in the home environment. The sensors output multiple binary sequences from which we know the existence/non-existence of persons under the sensors. The short duration averages of the binary responses are shown to be able to be regarded as pixel values of a top-view camera, but more advantageous in the sense of preserving privacy. Using the "pixel values" as features, support vector machine classifiers succeeded in recognizing eight activities (walking, reading, etc.) performed by five subjects at an average recognition rate of 80.65%. In addition, we proposed a martingale framework for detecting falls in this system. The experimental results showed that we attained the best performance of 95.14% (F1 value), the FAR of 7.5% and the FRR of 2.0%. This accuracy is not sufficient in general but surprisingly high with such low-level information. In summary, it is shown that this system has the potential to be used in the home environment to provide personalized services and to detect abnormalities of elders who live alone.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
The sensor module and the interconnection of sensor nodes with cables.
Figure 2.
Figure 2.
Side view of the detection area adjusted by a paper cylinder.
Figure 3.
Figure 3.
Layout of the home environment and the infrared sensors (top view).
Figure 4.
Figure 4.
Top view image sequence of a series of activities (the duration of walking, tidying the table, sitting on sofa, switching TV programs, leaving the room). Each image is selected in every two seconds. The gray level corresponds to the pixel value (darker is higher), each white dot shows the estimated position by Equation (2) at time t.
Figure 5.
Figure 5.
Activity strength (the sum of the 20 pixel values) of a series of activities in the home environment. Different colors show different activities.
Figure 6.
Figure 6.
Areas associated with each activity. Different colors show different activities.
Figure 7.
Figure 7.
The ground truth and recognition results of five users spending 4–5 minutes in the detection area. Different colors show different activities.
Figure 8.
Figure 8.
The variation of pixel values when a subject performs some activities. The gray level corresponds to the pixel value (darker is higher), the decimal numbers are the pixel values.
Figure 9.
Figure 9.
The variation of the pixel values, strangeness values and martingale values in a series of activities.
Figure 10.
Figure 10.
The ROC evaluation for different λ’s.
Figure 11.
Figure 11.
The martingale values when λ is set to 6 (red line) and 10 (blue line).
See this image and copyright information in PMC

References

    1. Haritaoglu I., Harwood D., Davis L. W4: Real-Time surveillance of people and their activities. IEEE Trans. Patt. Anal. Mach. Int. 2000;22:809–830.
    1. Hongeng S., Nevatia R., Bremond F. Video-Based event recognition: Activity representation and probabilistic recognition methods. Comput. Vis. Image Understand. 2004;96:129–162.
    1. Tao S., Kudo M., Nonaka H., Toyama J. Person Localization and Soft Authentication Using an Infrared Ceiling Sensor Network. In: Real P., Diaz-Pernil D., Molina-Abril H., Berciano A., Kropatsch W., editors. Computer Analysis of Images and Patterns. Vol. 6855. Springer; Heidelberg, Germany: 2011. pp. 122–129.
    1. Lee T., Lin T., Huang S., Lai S., Hung S. People Localization in a Camera Network Combining Background Subtraction and Scene-Aware Human Detection. In: Lee K.T., Tsai W.H., Liao H.Y., Chen T., Hsieh J.W., Tseng C.C., editors. Advances in Multimedia Modeling. Vol. 6523. Springer; Heidelberg, Germany: 2011. pp. 151–160.
    1. Hosokawa T., Kudo M., Nonaka H., Toyama J. Soft authentication using an infrared ceiling sensor network. Pattern Anal. Appl. 2009;12:237–249.

LinkOut - more resources