Abstract
For robots operating in real-world environments, the ability to deal with dynamic entities such as humans, animals, vehicles, or other robots is of fundamental importance. The variability of dynamic objects, however, is large in general, which makes it hard to manually design suitable models for their appearance and dynamics. In this paper, we present an unsupervised learning approach to this model-building problem. We describe an exemplar-based model for representing the time-varying appearance of objects in planar laser scans as well as a clustering procedure that builds a set of object classes from given observation sequences. Extensive experiments in real environments demonstrate that our system is able to autonomously learn useful models for, e.g., pedestrians, skaters, or cyclists without being provided with external class information.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Arras, K. O., Martínez Mozos, O., & Burgard, W. (2007). Using boosted features for the detection of people in 2d range data. In Proc. of the int. conf. on robotics & automation.
Chis, M., & Grosan, C. (2006) Evolutionary hierarchical time series clustering. In 6th int. conf. on intelligent systems design and applications (ISDA) (pp. 451–455). Washington, DC, USA.
Cui, J., Zha, H., Zhao, H., & Shibasaki, R. (2006). Robust tracking of multiple people in crowds using laser range scanners. In 18th int. conf. on pattern recognition (ICPR). Washington, DC, USA.
Cutler, R., & Davis, L. (2000). Robust real-time periodic motion detection, analysis, and applications. PAMI, 22(8), 781–796.
Drumwright, E., Jenkins, O. C., & Mataric, M. J. (2004). Exemplar-based primitives for humanoid movement classification and control. In Proc. of the int. conf. on robotics & automation (ICRA).
Fod, A., Howard, A., & Mataríc, M. (2001). Fast and robust tracking of multiple moving objects with a laser range finder. In Proc. of the int. conf. on robotics & automation (ICRA).
Fod, A., Howard, A., & Mataríc, M. (2002). Laser-based people tracking. In Proc. of the int. conf. on robotics & automation (ICRA).
Fortuna, J., & Capson, D. (2004). Ica filters for lighting invariant face recognition. In 17th int. conf. on pattern recognition (ICPR) (pp. 334–337). Washington, DC, USA.
Ghahramani, Z. (2004). Unsupervised learning. New York: Springer.
Hartigan, J. A. (1975). Clustering algorithms. New York: Wiley.
Ilg, W., Bakir, G., Mezger, J., & Giese, M. (2003). On the representation, learning and transfer of spatio-temporal movement characteristics. In Humanoids, July 2003, electronical version.
Jenkins, O. C., & Matarić, M. J. (2004). A spatio-temporal extension to Isomap nonlinear dimension reduction. In The int. conf. on machine learning (ICML) (pp. 441–448). Banff, Alberta, Canada, July 2004.
Kass, R. E., & Raftery, A. E. (1995). Bayes factors. Journal of the American Statistical Association, 90, 733–795.
Kruger, V., Zhou, S., & Chellappa, R. (2006). Integrating video information over time. example: Face recognition from video. In Cognitive vision systems (pp. 127–144). New York: Springer.
Lawrence, N. (2005). Probabilistic non-linear principal component analysis with Gaussian process latent variable models. Journal of Machine Learning Research, 6, 1783–1816.
MacLachlan, R., & Mertz, C. (2006). Tracking of moving objects from a moving vehicle using a scanning laser rangefinder. In Intelligent transportation systems 2006 (pp. 301–306). New York: IEEE.
Montemerlo, M., & Thrun, S. (2002). Conditional particle filters for simultaneous mobile robot localization and people tracking. In Proc. of the int. conf. on robotics & automation (ICRA).
Ng, H. T., & Lee, H. B. (1996). Integrating multiple knowledge sources to disambiguate word sense: An exemplar-based approach. In Proc. of the 34th annual meeting on association for computational linguistics (pp. 40–47).
Plagemann, C., Müller, T., & Burgard, W. (2005). Vision-based 3d object localization using probabilistic models of appearance. In Pattern recognition, 27th DAGM symposium, Vienna, Austria (Vol. 3663, pp. 184–191). New York: Springer.
Schulz, D. (2006). A probabilistic exemplar approach to combine laser and vision for person tracking. In Robotics: science and systems. Cambridge: The MIT Press.
Schulz, D., Burgard, W., Fox, D., & Cremers, A. (2001). Tracking multiple moving targets with a mobile robot using particle filters and statistical data association. In Proc. of the int. conf. on robotics & automation (ICRA).
Tasoulis, D. K., Adams, N. M., & Hand, D. J. (2006). Unsupervised clustering in streaming data. In 6th int. conf. on data mining—workshops (ICDMW) (pp. 638–642). Washington, DC.
Tenenbaum, J. B., de Silva, V., & Langford, J. C. (2000). A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500), 2319–2323.
Thrun, S. (2001). An probabilistic online mapping algorithm for teams of mobile robots. International Journal of Robotics Research, 20(5), 335–363.
Toyama, K., & Blake, A. (2002). Probabilistic tracking with exemplars in a metric space. International Journal of Computer Vision, 48(1), 9–19.
Wang, Y., & Han, J.-Q. (2005). Iris recognition using independent component analysis. Machine Learning and Cybernetics, 7, 4487–4492.
Wang, J. M., Fleet, D. J., & Hertzmann, A. (2006). Gaussian process dynamical models. In Advances in neural information processing systems (pp. 1441–1448). Cambridge: The MIT Press. Proc. NIPS’05.
Wren, C., Azarbayejani, A., Darrell, T., & Pentl, A. (1997). Pfinder: Real-time tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19, 780–785.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Luber, M., Arras, K.O., Plagemann, C. et al. Classifying dynamic objects. Auton Robot 26, 141–151 (2009). https://doi.org/10.1007/s10514-009-9112-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10514-009-9112-4