KI - Künstliche Intelligenz

, Volume 27, Issue 2, pp 161–167 | Cite as

From Object Recognition to Activity Interpretation and Back, Based on Point Cloud Data

  • Sven Albrecht
  • Thomas Wiemann
  • Joachim Hertzberg
  • Hans W. Guesgen
  • Stephen Marsland
Research Project

Abstract

Semantic mapping of static environments has become a hot topic in robotics. The aim of the Mermaid project was to investigate the transfer of a sensor data interpretation approach for mapping to the problem of activity recognition in smart home applications such as elderly care. The basic structure of the semantic mapping approach, i.e., to assemble hypotheses of object aggregates in a closed-loop process of bottom-up raw data interpretation and top-down expectation generation from a domain ontology, can be extended to the temporal domain to include activity interpretation. This paper reports initial results, based on a study using point clouds from depth (RGB-D) sensor data.

Keywords

Semantic mapping Activity recognition Smart home Symbol grounding 

References

  1. 1.
    Albrecht S, Wiemann T, Günther M, Hertzberg J (2011) Matching CAD object models in semantic mapping. In: Proc ICRA 2011 workshop on semantic perception, mapping and exploration Google Scholar
  2. 2.
    Allen JF (1983) Maintaining knowledge about temporal intervals. Commun ACM 26(11):832–843 MATHCrossRefGoogle Scholar
  3. 3.
    Bhatt M, Loke S (2008) Modelling dynamic spatial systems in the situation calculus. Spat Cogn Comput 8(1):86–130 Google Scholar
  4. 4.
    Bohlken W, Koopmann P, Neumann B (2011) Scenior: ontology-based interpretation of aircraft service activities. Tech rep FBI-HH-B-297/11, Department of Informatics, University of Hamburg Google Scholar
  5. 5.
    Chen L, Nugent C, Biswas J, Hoey J (eds) (2011) Activity recognition in pervasive intelligent environments. Atlantis Press, Amsterdam Google Scholar
  6. 6.
    Chua SL, Marsland S, Guesgen HW (2009) Behaviour recognition from sensory streams in smart environments. In: Proc AUS-AI Google Scholar
  7. 7.
    Chua SL, Marsland S, Guesgen HW (2009) Spatio-temporal and context reasoning in smart homes. In: Proc COSIT workshop on spatial and temporal reasoning for ambient intelligence systems. 2009 Google Scholar
  8. 8.
    Coradeschi S, Saffiotti A (2003) An introduction to the anchoring problem. J Robot Auton Syst 43(2–3):85–96 CrossRefGoogle Scholar
  9. 9.
    Galton AP (1993) Towards an integrated logic of space, time and motion. In: Proc IJCAI-93, pp 1550–1555 Google Scholar
  10. 10.
    Gao J, Hauptmann AG, Bharucha A, Wactlar HD (2004) Dining activity analysis using a hidden Markov model. In: Proc ICPR2004, pp 915–918 Google Scholar
  11. 11.
    Guesgen H, Marsland S (2011) Recognising human behaviour in a spatio-temporal context. In: Chong NY, Mastrogiovanni F (eds) Handbook of research on ambient intelligence and smart environments: trends and perspective. IGI Global, Hershey, pp 443–459 CrossRefGoogle Scholar
  12. 12.
    Guesgen HW, Marsland S (2010) Recognising human behaviour in a spatio-temporal context. IGI Global, Hershey Google Scholar
  13. 13.
    Günther M, Wiemann T, Albrecht S, Hertzberg J (2011) Model-based object recognition from 3d laser data. In: Proc KI-2011, pp 99–110 Google Scholar
  14. 14.
    Harnad S (1990) The symbol grounding problem. Physica D 42:335–346 CrossRefGoogle Scholar
  15. 15.
    Hertzberg J, Lingemann K, Nüchter A (2012) Mobile Roboter. Eine Einführung aus Sicht der Informatik. Springer-Vieweg, Berlin MATHGoogle Scholar
  16. 16.
    Hoppe H, DeRose T, Duchamp T, McDonald J, Stuetzle W (1992) Surface reconstruction from unorganized points. Comput Graph 26(2) Google Scholar
  17. 17.
    Kim D, Song J, Kim D (2007) Simultaneous gesture segmentation and recognition based on forward spotting accumulative HMMs. Pattern Recognit 40(11):3012–3026 MATHCrossRefGoogle Scholar
  18. 18.
    Kortenkamp D, Simmons R (2008) Robotic systems architectures and programming. In: Siciliano B, Khatib O (eds) Springer Handbook of Robotics. Springer, Berlin, pp 187–206, Chap 8 CrossRefGoogle Scholar
  19. 19.
    Lorensen WE, Cline HE (1987) Marching cubes: a high resolution 3D surface construction algorithm. In: ACM SIGGRAPH Google Scholar
  20. 20.
    Lyons P, Cong AT, Steinhauer HJ, Marsland S, Dietrich J, Guesgen HW (2010) Exploring the responsibilities of single-inhabitant smart homes with use cases. J Ambient Intell Smart Environ 2(3):211–232 Google Scholar
  21. 21.
    Neumann B, Möller R (2008) On scene interpretation with description logics. Image Vis Comput 26(1):82–101 CrossRefGoogle Scholar
  22. 22.
    Nilsson N (1984) Shakey the robot. Tech rep TN 323, SRI International Google Scholar
  23. 23.
    Nüchter A, Hertzberg J (2008) Towards semantic maps for mobile robots. J Robot Auton Syst 56(11):915–926 CrossRefGoogle Scholar
  24. 24.
    Schnabel R, Wahl R, Klein R (2007) Efficient ransac for point-cloud shape detection. Comput Graph Forum 26(2):214–226 CrossRefGoogle Scholar
  25. 25.
    Tapia EM, Intille SS, Larson K (2004) Activity recognition in the home using simple and ubiquitous sensors. In: Proc PERVASIVE, pp 158–175 Google Scholar
  26. 26.
    Wiemann T, Lingemann K, Nüchter A, Hertzberg J (2012) A toolkit for automatic generation of polygonal maps—Las Vegas reconstruction. In: Proc ROBOTIK-12, pp 446–451 Google Scholar
  27. 27.
    Wu JK, Dong L, Xiao W (2007) Real-time physical activity classification and tracking using wearable sensors. In: Proc ICICSP 2007, pp 1–6 Google Scholar
  28. 28.
    Zappi P, Stiefmeier T, Farella E, Roggen D, Benini L, Tröster G (2007) Activity recognition from on-body sensors by classifier fusion: sensor scalability and robustness. In: Proc ISSNIP’07, pp 281–286 Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Sven Albrecht
    • 1
  • Thomas Wiemann
    • 1
  • Joachim Hertzberg
    • 1
  • Hans W. Guesgen
    • 2
  • Stephen Marsland
    • 2
  1. 1.Institute of Computer ScienceOsnabrück UniversityOsnabrückGermany
  2. 2.School of Engineering and Advanced TechnologyMassey UniversityWellingtonNew Zealand

Personalised recommendations