Context-Aware Recognition of Drivable Terrain with Automated Parameters Estimation

  • Jan Wietrzykowski
  • Piotr SkrzypczyńskiEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 867)


This paper deals with the terrain classification problem for autonomous service robots in semi-structured outdoor environments. The aim is to recognize the drivable terrain in front of a robot that navigates on roads of different surfaces, avoiding areas that are considered non-drivable. Since the system should be robust to such factors as changing lighting conditions, mud and fallen leaves, we employ multi-sensor perception with a monocular camera and a 2D laser scanner. The labeling of the terrain obtained from a Random Trees classifier is refined by context-aware inference using the Conditional Random Field. We demonstrate that automatic learning of the parameters for Conditional Random Fields improves results in comparison to similar approaches without the context-aware inference or with parameters set by hand.


Vision Terrain classification Conditional Random Fields 


  1. 1.
    Belter, D., Łabȩcki, P., Skrzypczyński, P.: Estimating terrain elevation maps from sparse and uncertain multi-sensor data. In: Proceedings of IEEE International Conference on Robotics and Biomimetics, Guangzhou, pp. 715–722 (2012)Google Scholar
  2. 2.
    Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Fifth Annual Workshop on Computational Learning Theory, COLT 1992, pp. 144–152. ACM, New York (1992)Google Scholar
  3. 3.
    Breiman, L.: Random Forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar
  4. 4.
    Chetan, J., Krishna, M., Jawahar, C.: Fast and spatially-smooth terrain classification using monocular camera. In: International Conference on Pattern Recognition, Istanbul, pp. 4060–4063 (2010)Google Scholar
  5. 5.
    Dahlkamp, H., Kaehler, A., Stavens, D., Thrun, S., Bradski, G.: Self-supervised monocular road detection in desert terrain. In: Robotics: Science and Systems, Philadelphia (2006)Google Scholar
  6. 6.
    Hadsell, R., Sermanet, P., Ben, J., Erkan, A., Scoffier, M., Kavukcuoglu, K., Muller, U., LeCun, Y.: Learning long-range vision for autonomous off-road driving. J. Field Robot. 26(2), 120–144 (2009)CrossRefGoogle Scholar
  7. 7.
    Happold, M., Ollis, M., Johnson, N.: Enhancing supervised terrain classification with predictive unsupervised learning. In: Robotics: Science and Systems, Philadelphia (2006)Google Scholar
  8. 8.
    Häselich, M., Arends, M., Lang, D., Paulus, D.: Terrain classification with Markov random fields on fused camera and 3D laser range data. In: European Conference on Mobile Robots, Örebro, pp. 153–158 (2011)Google Scholar
  9. 9.
    Laible, S., Khan, Y.N., Zell, A.: Terrain Classification with conditional random fields on fused 3D LIDAR and camera data. In: European Conference on Mobile Robots (ECMR), Barcelona, pp. 172–177 (2013)Google Scholar
  10. 10.
    Laible, S., Zell, A.: Building local terrain maps using spatio-temporal classification for semantic robot localization. In: International Conference on Intelligent Robots and Systems, Chicago, pp. 4591–4597 (2014)Google Scholar
  11. 11.
    Nocedal, J.: Updating quasi-newton matrices with limited storage. Math. Comput. 35(151), 773–782 (1980)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Ojala, T., Pietikainen, M., Harwood, D.: Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. In: International Conference on Pattern Recognition, Jerusalem, pp. 582–585 (1994)Google Scholar
  13. 13.
    Ojeda, L., Borenstein, J., Witus, G., Karlsen, R.: Terrain characterization and classification with a mobile robot. J. Field Robot. 23(2), 103–122 (2006)CrossRefGoogle Scholar
  14. 14.
    Sutton, C., McCallum, A.: An introduction to conditional random fields. Found. Trends Mach. Learn. 4(4), 267–373 (2011)CrossRefGoogle Scholar
  15. 15.
    Wainwright, M.J., Jaakkola, T.S., Willsky, A.S.: Tree-based reparameterization framework for analysis of sum-product and related algorithms. IEEE Trans. Inf. Theory 49(5), 1120–1146 (2006)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Wainwright, M.J., Jordan, M.I.: Graphical models, exponential families, and variational inference. Found. Trends Mach. Learn. 1(1–2), 1–305 (2008)CrossRefGoogle Scholar
  17. 17.
    Wietrzykowski, J., Skrzypczyński, P.: Terrain classification for autonomous navigation in public urban areas. In: Silva, M. (ed.) Human-Centric Robotics, pp. 319–326. World-Scientific (2017)Google Scholar
  18. 18.
    Wietrzykowski, J., Belter, D.: Boosting support vector machines for RGB-D based terrain classification. J. Autom. Mob. Robot. Intell. Syst. 8(3), 28–34 (2014)Google Scholar
  19. 19.
    Wietrzykowski, J., Nowicki, M., Bondyra, A.: Exploring openstreetmap publicly available information for autonomous robot navigation. In: Szewczyk, R., et al. (eds.) Progress in Automation, Robotics and Measuring Techniques: Volume 2 Robotics, pp. 309–318. Springer, Cham (2015)Google Scholar
  20. 20.
    Wurm, K.M., Stachniss, C., Kümmerle, R., Burgard, W.: Improving robot navigation in structured outdoor environments by identifying vegetation from laser data. In: International Conference on Intelligent Robots and Systems, St. Louis, pp. 1217–1222 (2009)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Institute of Control, Robotics, and Information EngineeringPoznań University of TechnologyPoznańPoland

Personalised recommendations