Multi-scale Activity Estimation with Spatial Abstractions

  • Majd HawaslyEmail author
  • Florian T. Pokorny
  • Subramanian Ramamoorthy
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10589)


Estimation and forecasting of dynamic state are fundamental to the design of autonomous systems such as intelligent robots. State-of-the-art algorithms, such as the particle filter, face computational limitations when needing to maintain beliefs over a hypothesis space that is made large by the dynamic nature of the environment. We propose an algorithm that utilises a hierarchy of such filters, exploiting a filtration arising from the geometry of the underlying hypothesis space. In addition to computational savings, such a method can accommodate the availability of evidence at varying degrees of coarseness. We show, using synthetic trajectory datasets, that our method achieves a better normalised error in prediction and better time to convergence to a true class when compared against baselines that do not similarly exploit geometric structure.


  1. 1.
    Belta, C., Bicchi, A., Egerstedt, M., Frazzoli, E., Klavins, E., Pappas, G.: Symbolic planning and control of robot motion [grand challenges of robotics]. Robot. Autom. Mag. 14(1), 61–70 (2007)CrossRefGoogle Scholar
  2. 2.
    Brandao, B.C., Wainer, J., Goldenstein, S.K.: Subspace hierarchical particle filter. In: 19th Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2006, pp. 194–204. IEEE (2006)Google Scholar
  3. 3.
    Burridge, R.R., Rizzi, A.A., Koditschek, D.E.: Sequential composition of dynamically dexterous robot behaviors. Int. J. Robot. Res. 18(6), 534–555 (1999)CrossRefGoogle Scholar
  4. 4.
    Eiter, T., Mannila, H.: Computing discrete Fréchet distance. Technical report CD-TR 94/64. Technical University of Vienna (1994)Google Scholar
  5. 5.
    Kuipers, B.: The spatial semantic hierarchy. Artif. Intell. 119(1), 191–233 (2000)CrossRefzbMATHMathSciNetGoogle Scholar
  6. 6.
    MacCormick, J., Isard, M.: Partitioned sampling, articulated objects, and interface-quality hand tracking. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 3–19. Springer, Heidelberg (2000). doi: 10.1007/3-540-45053-X_1 CrossRefGoogle Scholar
  7. 7.
    Müllner, D.: Modern hierarchical, agglomerative clustering algorithms. arXiv preprint arXiv:1109.2378 (2011)
  8. 8.
    Pokorny, F.T., Hawasly, M., Ramamoorthy, S.: Multiscale topological trajectory classification with persistent homology. In: Robotics: Science and Systems (2014)Google Scholar
  9. 9.
    Pokorny, F.T., Hawasly, M., Ramamoorthy, S.: Topological trajectory classification with filtrations of simplicial complexes and persistent homology. Int. J. Robot. Res. 35, 201–223 (2015)Google Scholar
  10. 10.
    Shabat, G., Shmueli, Y., Bermanis, A., Averbuch, A.: Accelerating particle filter using randomized multiscale and fast multipole type methods. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2015)Google Scholar
  11. 11.
    Verma, V., Thrun, S., Simmons, R.: Variable resolution particle filter. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 976–984 (2003)Google Scholar
  12. 12.
    Xu, R., Wunsch, D.I.: Survey of clustering algorithms. IEEE Trans. Neural Netw. 16(3), 645–678 (2005)CrossRefGoogle Scholar
  13. 13.
    Yang, C., Duraiswami, R., Davis, L.: Fast multiple object tracking via a hierarchical particle filter. In: Tenth IEEE International Conference on Computer Vision (ICCV), vol. 1, pp. 212–219 (2005)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Majd Hawasly
    • 1
    Email author
  • Florian T. Pokorny
    • 2
  • Subramanian Ramamoorthy
    • 3
  1. 1.FiveAI Inc.EdinburghUK
  2. 2.KTH Royal Institute of TechnologyStockholmSweden
  3. 3.School of InformaticsThe University of EdinburghEdinburghUK

Personalised recommendations