Journal of Internet Computing and Services (인터넷정보학회논문지)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지

Human Activity Recognition using an Image Sensor and a 3-axis Accelerometer Sensor

이미지 센서와 3축 가속도 센서를 이용한 인간 행동 인식

  • 남윤영 (아주대학교 유비쿼터스컨버전스연구소) ;
  • 최유주 (서울벤처정보대학원대학교 컴퓨터응용기술학과) ;
  • 조위덕 (아주대학교 전자공학부)
  • Published : 2010.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we present a wearable intelligent device based on multi-sensor for monitoring human activity. In order to recognize multiple activities, we developed activity recognition algorithms utilizing an image sensor and a 3-axis accelerometer sensor. We proposed a grid?based optical flow method and used a SVM classifier to analyze data acquired from multi-sensor. We used the direction and the magnitude of motion vectors extracted from the image sensor. We computed the correlation between axes and the magnitude of the FFT with data extracted from the 3-axis accelerometer sensor. In the experimental results, we showed that the accuracy of activity recognition based on the only image sensor, the only 3-axis accelerometer sensor, and the proposed multi-sensor method was 55.57%, 89.97%, and 89.97% respectively.

본 논문에서는 사람의 행동 모니터링을 위한 멀티 센서 기반의 웨어러블 지능형 디바이스를 제안한다. 다중 행동을 인식하기 위해, 이미지 센서와 가속도 센서를 이용하여 행동 인식 알고리즘을 개발하였다. 멀티 센서로부터 얻은 데이터를 분석하기 위해 그리드 기반 옵티컬 플로우 방법을 제안하고 SVM 분류기법을 이용하였다. 이미지 센서로부터 얻은 모션 벡터의 방향과 크기를 이용하였고, 3축 가속도 센서로부터 얻은 데이터에서 FFT의 축과 크기와의 상관관계를 계산하였다. 실험 결과에서 이미지 센서 기반과 3축 가속도 센서기반의 행동 인식률은 각각 55.57 %, 89.97%를 보였으나 제안한 멀티센서기반의 행동인식률은 92.78% 를 보였다.

Keywords

References

  1. N. Kern, B. Schiele, A. Schmidt, "Multi-Sensor Activity Context Detection for Wearable Computing", Ambient Intelligence LNCS, pp. 220-232, October 17 2003.
  2. A. Krause, D. Siewiore, A. Smailagic, J. Farringdon, "Unsupervised, Dynamic Identification of Physiological and Activity Context in Wearable Computing", Proceedings Seventh IEEE International Symposium, pp. 88-97, October 18-21. 2005.
  3. N. Ravi, N. Dandekar, P. Mysore, M. Littman, "Activity Recognition from Accelerometer Data", the Seventeenth Innovative Applications of Artificial Intelligence Conference, pp. 11-1, July 2005.
  4. L. Bao, S. Intille, "Activity Recognition from User-Annotated Acceleration Data", PERVASIVE 2004, LNCS 3001, pp. 1-17, Berlin, 2005.
  5. R.W. DeVaul, S. Dunn, "Real-time motion classification for wearable computing applications", Technical report, MIT Midea Lab., 2001.
  6. T. Hyuhn, B. Schiele, "Analyzing Features for Activity Recognition", Proceedings of the 2005 joint conference on Smart objects and ambient intelligence, Grenoble, France, pp. 159-163, October 2005.
  7. J. Caros, et al., "Very Low Complexity Algorithm for Ambulatory Activity Classification," 3rd European Medical and Biological Conference EMBEC, 2005.
  8. Z. Husz, A. Wallace, P. Green, "Human activity ecognition with action primitives", AVSS2007, London, pp. 330-335, September 2007.
  9. T. Nakata, "Recognizing Human Activities in Video by Multi-resolutional Optical Flows", Intelligent Robots and Systems, 2006 IEEE/RSJ International Conference, Beijing, China, pp. 1793-1798, 2006.
  10. Y. Cho, Y. Nam, T. Kim, J. Kim, and W. Cho, "SmartPendant: An Intelligent Device for human activity recognition and Location tracking", KCC, pp. 340-344, October 2007.
  11. C. Zhu, W. Sheng, "Multi-sensor fusion for human daily activity recognition in robot-assisted living", HRI 2009: pp. 303-304
  12. P. Burt and E. Adelson, "The Laplacian Pyramid as a Compact Image Code" IEEE Transactions on communication, Vol. com-31, No. 4, pp. 532-540, April, 1983.
  13. B. Lucas and T. Kanade, "An iterative image registration technique with an application to stereo vision," in DARPA Image Understanding Workshop. DARPA, pp. 121-130, 1981.
  14. J. Barron, D. Fleet, and S. Beauchemin. "Performance of optical flow techniques," International Journal of Computer Vision, vol. 12, no. 1, pp. 43-77, 1995.
  15. N. Ravi, N. Dandekar, P. Mysore, and M. L. Littman, "Activity recognition from accelerometer data," In AAAI, pages 1541-1546, 2005.
  16. M. Losch, S. Schmidt-Rohr, S. Knoop, S. Vacek, and R. Dillmann, "Feature set selection and optimal classifier for human activity recognition," in ROMAN, Korea, Aug 2007.
  17. Open Source Computer Vision Library, http://www.intel.com/research/mrl/research/opencv.