Advertisement

Recognizing Soldier Activities in the Field

  • David Minnen
  • Tracy Westeyn
  • Daniel Ashbrook
  • Peter Presti
  • Thad Starner
Part of the IFMBE Proceedings book series (IFMBE, volume 13)

Abstract

We describe the activity recognition component of the Soldier Assist System (SAS), which was built to meet the goals of DARPA’s Advanced Soldier Sensor Information System and Technology (ASSIST) program. As a whole, SAS provides an integrated solution that includes on-body data capture, automatic recognition of soldier activity, and a multimedia interface that combines data search and exploration. The recognition component analyzes readings from six on-body accelerometers to identify activity. The activities are modeled by boosted 1D classifiers, which allows efficient selection of the most useful features within the learning algorithm. We present empirical results based on data collected at Georgia Tech and at the Army’s Aberdeen Proving Grounds during official testing by a DARPA appointed NIST evaluation team. Our approach achieves 78.7% for continuous event recognition and 70.3% frame level accuracy. The accuracy increases to 90.3% and 90.3% respectively when considering only the modeled activities. In addition to standard error metrics, we discuss error division diagrams (EDDs) for several Aberdeen data sequences to provide a rich visual representation of the performance of our system.

Keywords

activity recognition machine learning distributed sensors 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    DARPA, “ASSIST BAA #04-38, http://www.darpa.mil/ipto/solicitations/open/04-38 PIP.htm,” November 2006.Google Scholar
  2. [2]
    J. Ward, P. Lukowicz, and G. Tröster, “Evaluating performance in continuous context recognition using event-driven error characterisation,” in Proceedings of LoCA 2006, May 2006, pp. 239–255.Google Scholar
  3. [3]
    N. Kern, S. Antifakos, B. Schiele, and A. Schwaninger, “A model for human interruptability: Experimental evaluation and automatic estimation from wearable sensors.” in ISWC. IEEE Computer Society, 2004, pp. 158–165.Google Scholar
  4. [4]
    M. Stäger, P. Lukowicz, N. Perera, T. von Büren, G. Tröster, and T. Starner, “Soundbutton: Design of a low power wearable audio classification system.” in ISWC. IEEE Computer Society, 2003, pp. 12–17.Google Scholar
  5. [5]
    P. Lukowicz, J. Ward, H. Junker, M. Stäger, G. Tröster, A. Atrash, and T. Starner, “Recognizing workshop activity using body worn microphones and accelerometers,” in Pervasive Computing, 2004, pp. 18–22.Google Scholar
  6. [6]
    T. Westeyn, K. Vadas, X. Bian, T. Starner, and G. D. Abowd, “Recognizing mimicked autistic self-stimulatory behaviors using hmms.” in Ninth IEEE Int. Symp. on Wearable Computers, October 18–21 2005, pp. 164–169.Google Scholar
  7. [7]
    L. Bao and S. S. Intille, “Activity recognition from user-annotated acceleration data,” in Pervasive. Berlin Heidelberg: Springer-Verlag, 2004, pp. 1–17.Google Scholar
  8. [8]
    J. Lester, T. Choudhury, N. Kern, G. Borriello, and B. Hannaford, “A hybrid discriminative/generative approach for modeling human activities,” in Nineteenth International Joint Conference on Artificial Intelligence, July 30–August 5 2005, pp. 766–772.Google Scholar
  9. [9]
    A. Raj, A. Subramanya, D. Fox, and J. Bilmes, “Rao-blackwellized particle filters for recognizing activities and spatial context from wearable sensors,” in Experimental Robotics: The 10th International Symposium, 2006.Google Scholar
  10. [10]
    R. E. Schapire, “A brief introduction to boosting,” in IJCAI, 1999, pp. 1401–1406.Google Scholar
  11. [11]
    P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Computer Vision and Pattern Recognition, 2001.Google Scholar
  12. [12]
    J. Platt, “Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods,” in Advances in Large Margin Classifiers. MIT Press, 1999.Google Scholar
  13. [13]
    D. Minnen, T. Westeyn, T. Starner, J. Ward, and P. Lukowicz, “Performance metrics and evaluation issues for continuous activity recognition,” in Performance Metrics for Intelligent Systems, 2006.Google Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2007

Authors and Affiliations

  • David Minnen
    • 1
  • Tracy Westeyn
    • 1
  • Daniel Ashbrook
    • 1
  • Peter Presti
    • 2
  • Thad Starner
    • 1
  1. 1.Georgia Institute of TechnologyCollege of Computing, GVUAtlantaUSA
  2. 2.Interactive Media Technology CenterGeorgia Institute of TechnologyAtlantaUSA

Personalised recommendations