Skip to main content

Combining discriminative spatiotemporal features for daily life activity recognition using wearable motion sensing suit

Abstract

Motion sensing plays an important role in the study of human movements, motivated by a wide range of applications in different fields, such as sports, health care, daily activity, action recognition for surveillance, assisted living and the entertainment industry. In this paper, we describe how to classify a set of human movements comprising daily activities using a wearable motion capture suit, denoted as FatoXtract. A probabilistic integration of different classifiers recently proposed is employed herein, considering several spatiotemporal features, in order to classify daily activities. The classification model relies on the computed confidence belief from base classifiers, combining multiple likelihoods from three different classifiers, namely Naïve Bayes, artificial neural networks and support vector machines, into a single form, by assigning weights from an uncertainty measure to counterbalance the posterior probability. In order to attain an improved performance on the overall classification accuracy, multiple features in time domain (e.g., velocity) and frequency domain (e.g., fast Fourier transform), combined with geometrical features (joint rotations), were considered. A dataset from five daily activities performed by six participants was acquired using FatoXtract. The dataset provided in this work was designed to be extremely challenging since there are high intra-class variations, the duration of the action clips varies dramatically, and some of the actions are quite similar (e.g., brushing teeth and waving, or walking and step). Reported results, in terms of both precision and recall, remained around 85 %, showing that the proposed framework is able to successfully classify different human activities.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Notes

  1. 1.

    http://www.ingeniarius.pt/?page=fatoxtract.

  2. 2.

    http://www.cs.waikato.ac.nz/ml/weka/.

  3. 3.

    https://www.youtube.com/watch?v=607NR5xVD3c.

  4. 4.

    https://www.youtube.com/watch?v=607NR5xVD3c.

References

  1. 1.

    Aggarwal JK, Cai Q (1999) Human motion analysis: a review. Comput Vis Image Underst 73(3):428–440

    Article  Google Scholar 

  2. 2.

    Zhou H, Hu H (2008) Human motion tracking for rehabilitation—a survey. Biomed Signal Process Control 3(1):1–18

    Article  Google Scholar 

  3. 3.

    Chen X (2013) Human motion analysis with wearable inertial. PhD thesis

  4. 4.

    Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin

    MATH  Google Scholar 

  5. 5.

    Yegnanarayana B (2009) Artificial neural networks. PHI Learning Pvt. Ltd., New Delhi

    Google Scholar 

  6. 6.

    Tong S, Koller D (2001) Support vector machine active learning with applications to text classification. J Mach Learn Res 2:45–66

    MATH  Google Scholar 

  7. 7.

    Mittal A, Kassim A (2007) Bayesian network technologies: applications and graphical models. IGI Global, Hershey

    Book  Google Scholar 

  8. 8.

    Faria DR, Vieira M, Premebida C, Nunes U (2015) Probabilistic human daily activity recognition towards robot-assisted living. In: Proceedings of IEEE RO-MAN’15: IEEE international symposium on robot and human interactive communication

  9. 9.

    Faria DR, Premebida C, Nunes U (2014) A probabilistic approach for human everyday activities recognition using body motion from RGB-D images. In: Robot and human interactive communication, 2014 RO-MAN: IEEE international symposium, pp 732–737

  10. 10.

    Bao L, Intille SS (2004) Activity recognition from user-annotated acceleration data. In: Ferscha A, Mattern F (eds) Pervasive computing. Springer, Berlin, Heidelberg, pp 1–17

    Google Scholar 

  11. 11.

    Huynh T (2008) Human activity recognition with wearable sensors. PhD thesis, Technische Universität Darmstadt

  12. 12.

    Huynh T, Schiele B (2005) Analyzing features for activity recognition. In: Proceedings of the 2005 joint conference on smart objects and ambient intelligence: innovative context-aware services: usages and technologies

  13. 13.

    Suutala J, Pirttikangas S, Röning J (2007) Discriminative temporal smoothing for activity recognition from wearable sensors. In: Ichikawa H, Cho W-D, Satoh I, Youn HY (eds) Ubiquitous computing systems. Springer, Berlin, Heidelberg, pp 182–195

    Chapter  Google Scholar 

  14. 14.

    Fusier F, Valentin V, Bremond F, Thonnat M, Borg M, Thirde D, Ferryman J (2007) Video understanding for complex activity recognition. Mach Vis Appl 18(3–4):167–188

    Article  MATH  Google Scholar 

  15. 15.

    Chen M-Y, Hauptmann A (2009) Mosift: recognizing human actions in surveillance videos. School of Computer Science, Carnegie Mellon University, Pittsburgh

    Google Scholar 

  16. 16.

    Carling C, Bloomfield J, Nelsen L, Reilly T (2008) The role of motion analysis in elite soccer. Sports Med 38(10):839–862

    Article  Google Scholar 

  17. 17.

    Ermes M, Parkk J (2008) Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. In: IEEE transactions on information technology in biomedicine, pp 20–26

  18. 18.

    Beek PJ, Peper CE, Stegeman DF (1995) Dynamical models of movement coordination. Hum Mov Sci 14(4):573–608

    Article  Google Scholar 

  19. 19.

    Vital JP, Couceiro MS, Dias G, Ferreira NM (2015) Tecnologias para a análise do movimento humano. In: Ruben R, Vieira M, Campos C, Almeida H, Siopa J, Bártolo P, Folgado J (eds) 6º Congresso nacional de biomecânica, ESTG – Instituto Politécnico de Leiria, pp 1–6

  20. 20.

    Barbosa C (2011) Modelação biomecânica do corpo humano: aplicação na análise da marcha. MSc Thesis

  21. 21.

    Tao W, Liu T, Zheng R, Feng H (2012) Gait analysis using wearable sensors. Sensors 12(2):2255–2283

    Article  Google Scholar 

  22. 22.

    Lara ÓD, Labrador MA (2013) A survey on human activity recognition using wearable sensors. Commun Surv Tutor IEEE 15(3):1192–1209

    Article  Google Scholar 

  23. 23.

    Kohavi R (1995) The power of decision tables. In: Machine learning: ECML-95

  24. 24.

    Aha DW, Kibler D, Albert MK (1991) Instance-based learning algorithms. Mach Learn 6(1):37–66

    Google Scholar 

  25. 25.

    Safavian SR, Landgrebe D (1991) A survey of decision tree classifier methodology. IEEE Trans Syst Man Cybern 21(3):660–674

    Article  MathSciNet  Google Scholar 

  26. 26.

    Rish I (2001) An empirical study of the naive Bayes classifier. In: IJCAI 2001 workshop on empirical methods in artificial intelligence, vol 3, no 22, pp 41–46

  27. 27.

    Yamato J, Ohya J, Ishii K (1992) Recognizing human action in time-sequential images using hidden markov model. In: Computer vision and pattern recognition

  28. 28.

    Zhang M, Sawchuk AA (2013) Human daily activity recognition with sparse representation using wearable sensors. IEEE J Biomed Health Inform 17(3):553–560

    Article  Google Scholar 

  29. 29.

    Khoshhal K, Aliakbarpour H, Quintas J, Drews P, Dias J (2010) Probabilistic LMA-based classification of human behaviour understanding using power spectrum technique. In: Information fusion (FUSION)

  30. 30.

    Avci A, Bosch S, Marin-Perianu M, Havinga P (2010) Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: a survey. In: 23rd international conference in architecture of computing systems (ARCS), 2010

  31. 31.

    Zhu C, Sheng W (2009) Human daily activity recognition in robot-assisted living using multi-sensor fusion. In: IEEE international conference in robotics and automation, ICRA’09

  32. 32.

    Hong Y-J, Kim I-J, Ahn SC, Kim H-G (2008) Activity recognition using wearable sensors for elder care. In: International conference on in future generation communication and networking, (FGCN’08)

  33. 33.

    Arsigny V, Fillard P, Pennec X, Ayache N (2006) Log-euclidean metrics for fast and simple calculus on diffusion tensors. Magn Reson Med 56(2):411–421

    Article  Google Scholar 

  34. 34.

    Guo K (2012) Action recognition using log-covariance matrices of silhouette and optical-flow features. PhD. dissertation, Boston University, College of Engineering

  35. 35.

    Uddin MZ, Thang ND, Kim JT, Kim T-S (2011) Human activity recognition using body joint-angle features and hidden Markov model. ETRI J 33(4):569–579

    Article  Google Scholar 

  36. 36.

    Jackson JE (2005) A user’s guide to principal components, vol 587. Wiley, Hoboken

    MATH  Google Scholar 

  37. 37.

    Jolliffe IT (2002) Principal component analysis. Wiley, Hoboken

    MATH  Google Scholar 

  38. 38.

    Krzanowski W (2000) Principles of multivariate analysis. Oxford University Press, Oxford

    MATH  Google Scholar 

  39. 39.

    Seber GA (2009) Multivariate observations, vol 252. Wiley, Oxford

    MATH  Google Scholar 

  40. 40.

    Premebida C, Faria DR, de Souza FA, Nunes U (2015) Applying probabilistic mixture models to semantic place classification in mobile robotics. In: Proceedings of IEEE IROS’15: IEEE international conference on intelligent robots and systems. Hamburg, Germany

  41. 41.

    Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6(2):461–464

    Article  MATH  MathSciNet  Google Scholar 

  42. 42.

    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297

    MATH  Google Scholar 

  43. 43.

    Vapnik V (1998) Statistical learning theory, vol 1. Wiley, New York

    MATH  Google Scholar 

  44. 44.

    Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector. ACM Trans Intell Syst Technol (TIST) 2(3):27

    Google Scholar 

  45. 45.

    Couceiro MS, Dias G, Mendes R, Araújo D (2013) Accuracy of pattern detection methods in the performance of golf putting. J Mot Behav 45(1):37–53

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Jessica P. M. Vital.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Vital, J.P.M., Faria, D.R., Dias, G. et al. Combining discriminative spatiotemporal features for daily life activity recognition using wearable motion sensing suit. Pattern Anal Applic 20, 1179–1194 (2017). https://doi.org/10.1007/s10044-016-0558-7

Download citation

Keywords

  • Pattern recognition
  • Feature extraction
  • Classification methods
  • Human movement analysis
  • Motion capture suit