Advertisement

Catalogue-Based Traffic Sign Asset Management: Towards User’s Effort Minimisation

  • Kelwin FernandesEmail author
  • Pedro F. B. Silva
  • Lucian Ciobanu
  • Paulo Fonseca
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8814)

Abstract

Automatic traffic sign recognition is a difficult task, as it is necessary to distinguish between a very high number of classes with low inter-class variability. The state-of-the-art methods report very high accuracy rates but just a few classes are covered and several training samples are required. For the sake of the development of an asset management system, these approaches are out of reach. Furthermore, in this context, minimizing user’s effort is more important than achieving maximal classification accuracy. In this paper, we propose a catalogue-based traffic sign classifier which doesn’t require real training samples for model building and promotes minimal user’s workload involving the catalogue’s semantic structure in the error propagation. Experimental results reveal that user’s workload was reduced by 20 % while accuracy was improved by 2 %.

Keywords

Traffic sign recognition Discriminative local regions Distance transform Traffic sign asset management User centered machine learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ruta, A., Li, Y., Liu, X.: Real-time traffic sign recognition from video by class-specific discriminative features. Pattern Recogn. 43(1), 416–430 (2010)CrossRefzbMATHGoogle Scholar
  2. 2.
    Broggi, A., Cerri, P., Medici, P., Porta, P., Ghisio, G.: Real time road signs recognition. In: 2007 IEEE Intelligent Vehicles Symposium, pp. 981–986 (June 2007)Google Scholar
  3. 3.
    Bahlmann, C., Zhu, Y., Ramesh, V., Pellkofer, M., Koehler, T.: A system for traffic sign detection, tracking, and recognition using color, shape, and motion information. In: Proceedings of the Intelligent Vehicles Symposium, pp. 255–260. IEEE (June 2005)Google Scholar
  4. 4.
    Moutarde, F., Bargeton, A., Herbin, A., Chanussot, L.: Modular traffic sign recognition applied to on-vehicle real-time visual detection of american and european speed limit signs. CoRR (2009)Google Scholar
  5. 5.
    Ciresan, D., Meier, U., Masci, J., Schmidhuber, J.: A committee of neural networks for traffic sign classification. In: The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 1918–1921. IEEE (2011)Google Scholar
  6. 6.
    Moutarde, F., Bargeton, A., Herbin, A., Chanussot, L.: Robust on-vehicle real-time visual detection of american and european speed limit signs, with a modular traffic signs recognition system. In: 2007 IEEE Intelligent Vehicles Symposium, pp. 1122–1126 (June 2007)Google Scholar
  7. 7.
    Culotta, A., McCallum, A.: Reducing labeling effort for structured prediction tasks. In: Veloso, M.M., Kambhampati, S. (eds.), pp. 746–751. AAAI Press/The MIT Press (2005)Google Scholar
  8. 8.
    Diário da Républica: http://aiweb.techfak.uni-bielefeld.de/content/bworld-robot-control-software/ I Série B N\(^\circ \) 227 (October 1, 1998)

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Kelwin Fernandes
    • 1
    Email author
  • Pedro F. B. Silva
    • 1
  • Lucian Ciobanu
    • 1
  • Paulo Fonseca
    • 2
  1. 1.INESC TECPortoPortugal
  2. 2.MonteAdrianoGrupo ElevoPortoPortugal

Personalised recommendations