Dempster-Shafer Fusion of Context Sources for Pedestrian Recognition

Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 164)

Abstract

This contribution presents the design of an image-based contextual pedestrian classifier for an automotive application. Our previous work shows that local classifiers working with image cutouts are in many cases not sufficient to achieve satisfactory results in complex scenarios. As a solution the work proposed incorporating contextual knowledge into the classification task, significantly improving the classification results. Contextual knowledge is described by a set of different and independent context sources. This paper discusses the fusion of these sources on the basis of the Dempster-Shafer theory. It presents and compares different possibilities to model the frame of discernment and the mass function to achieve optimal results. Furthermore, it provides an elegant way to take uncertainties of the context sources into account. The methods are evaluated on simulated and on real data.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Forbes, C., Evans, M., Hastings, N., Peacock, B.: Statistical Distributions. John Wiley & Sons (2011)Google Scholar
  2. 2.
    Ristic, B., Smets, P.: Belief function theory on the continuous space with an application to model based classification. In: Information Processing and Management of Uncertainty (2004)Google Scholar
  3. 3.
    Smets, P.: The combination of evidence in the transferable belief model. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(5), 447–458 (1990)CrossRefGoogle Scholar
  4. 4.
    Szczot, M., Dannenmann, I., Lohlein, O.: Incorporating lane estimation as context source in pedestrian recognition task. In: ICPR (2010)Google Scholar
  5. 5.
    Szczot, M., Löhlein, O., Palm, G.: Incorporating contextual information in pedestrian recognition. In: The IEEE Intelligent Vehicles Symposium, IV (2009)Google Scholar
  6. 6.
    Viola, P., Jones, M.: Robust real-time object detection. In: Proceedings of IEEE Workshop on Statistical and Computational Theories of Vision (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Magdalena Szczot
    • 1
  • Otto Löhlein
    • 2
  • Günther Palm
    • 3
  1. 1.University of UlmUlmGermany
  2. 2.Department Environment Perception (GR/PAP)Daimler AGUlmGermany
  3. 3.Institute of Neural Information ProcessingUniversity of UlmUlmGermany

Personalised recommendations