Journal of Intelligent and Robotic Systems

, Volume 40, Issue 3, pp 267–297 | Cite as

Line Extraction in 2D Range Images for Mobile Robotics

  • Geovany Araujo Borges
  • Marie-José Aldon


This paper presents a geometrical feature detection framework for use with conventional 2D laser rangefinders. This framework is composed of three main procedures: data pre-processing, breakpoint detection and line extraction. In data pre-processing, low-level data organization and processing are discussed, with emphasis to sensor bias compensation. Breakpoint detection allows to determine sequences of measurements which are not interrupted by scanning surface changing. Two breakpoint detectors are investigated, one based on adaptive thresholding, and the other on Kalman filtering. Implementation and tuning of both detectors are also investigated. Line extraction is performed to each continuous scan sequence in a range image by applying line kernels. We have investigated two classic kernels, commonly used in mobile robots, and our Split-and-Merge Fuzzy (SMF) line extractor. SMF employs fuzzy clustering in a split-and-merge framework without the need to guess the number of clusters. Qualitative and quantitative comparisons using simulated and real images illustrate the main characteristics of the framework when using different methods for breakpoint and line detection. These comparisons illustrate the characteristics of each estimator, which can be exploited according to the platform computing power and the application accuracy requirements.

line extraction breakpoint detection 2D range images local environments environment modeling mobile robotics Fuzzy C-means linear Kalman filter 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Arras, K. O., Tomatis, N., Jensen, B. T. and Siegwart, R.: 2001, Multisensor on-the-fly localization: Precision and reliability for applications, Robotics and Autonomous Systems 34, 131–143.CrossRefGoogle Scholar
  2. Barni, M., Cappellini, V., Paoli, A. and Mecocci, A.: 1996, Unsupervised detection of straight lines through possibilistic clustering, in: IEEE International Conference on Image Processing, pp. 963–966.Google Scholar
  3. Bar-Shalom, Y. and Fortmann, T. E.: 1987, Tracking and Data Association, Academic Press, London, U.K.Google Scholar
  4. Bezdek, J. C.: 1981, Pattern Recognition With Fuzzy Objective Function Algorithms, Plenum Press, New York.Google Scholar
  5. Borenstein, J., Everett, H. R. and Feng, L.: 1996, Navigating Mobile Robots: Systems and Techniques, A. K. Peters, Wellesley, MA.Google Scholar
  6. Borges, G. A. and Aldon, M.-J.: 2000, A Split-and-Merge segmentation algorithm for line extractions in 2-D range images, in: Proc of 15th International Conference on Pattern Recognition.Google Scholar
  7. Borges, G. A., Aldon, M.-J. and Gil, T.: 2001, An optimal pose estimator for map-based mobile robot dynamic localization: Experimental comparison with the EKF, in: IEEE International Conference on Robotics and Automation.Google Scholar
  8. Borges, G. A. and Aldon, M.-J.: 2001, Design of a robust real-time dynamic localization system for mobile robots, in: 9th International Symposium on Intelligent Robotic Systems, Toulouse, France.Google Scholar
  9. Borges, G. A. and Aldon, M.-J.: 2002, A decoupled approach for simultaneous stochastic mapping and mobile robot localization, in: IEEE/RSJ International Conference on Intelligent Robots and Systems.Google Scholar
  10. Borges, G. A. and Aldon, M.-J.: 2003, Robustified estimation algorithms for mobile robot localization based on geometrical environment maps, Robotics and Autonomous Systems 45(3–4), 131–159.CrossRefGoogle Scholar
  11. Castellanos, J. A. and Tardós, J. D.: 1996, Laser-based segmentation and localization for a mobile robot, in: M. Jamshidi, F. Pin and P. Dauchez (eds.), Robotics and Manufacturing: Recent Trends in Research and Applications, Vol. 6, ASME Press.Google Scholar
  12. Davé, R. N. and Krishnapuram, R.: 1997, Robust clustering methods: A unified view, IEEE Transactions on Fuzzy Systems 5(7), 270–293.CrossRefGoogle Scholar
  13. Duda, R. O. and Hart, P. E.: 1973, Pattern Classification and Scene Analysis, Wiley, New York.Google Scholar
  14. Einsele, T.: 1997, Real-time self-localization in unknown indoor environments using a panorama laser range finder, in: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 697–702.Google Scholar
  15. Forsberg, J., Larsson, U. and Wernersson, Å.: 1995, Mobile robot navigation using the rangeweighted Hough transform, IEEE Robotics and Automation Magazine, 18–26.Google Scholar
  16. Frigui, H. and Krishnapuram, R.: 1999, A robust competitive clustering algorithm with applications in computer vision, IEEE Transactions on Pattern Analysis and Machine Intelligence 21(5), 450–465.CrossRefGoogle Scholar
  17. Haralick, R. M.: 1994, Propagating covariances in computer vision, in: International Conference on Pattern Recognition, pp. 493–498.Google Scholar
  18. Jazwinski, A. H.: 1970, Stochastic Processes and Filtering Theory, Academic Press, New York.Google Scholar
  19. Jensfelt, P. and Christensen, H. I.: 1998, Laser based position acquisition and tracking in an indoor environment, in: International Symposium on Robotics and Automation, pp. 331–338.Google Scholar
  20. Jolion, J. M., Meer, P. and Bataouche, S.: 1991, Robust clustering with applications in computer vision, IEEE Transactions on Pattern Analysis and Machine Intelligence 13(8), 791–802.CrossRefGoogle Scholar
  21. Kämpke, T. and Strobel, M.: 2001, Polygonal model fitting, J. Intelligent Robotic Systems 30, 279–310.CrossRefGoogle Scholar
  22. Kwon, Y. D. and Lee, J. S.: 1999, A stochastic environment map building method for mobile robot using 2-D laser range finder, Autonomous Robots 7, 187–200.CrossRefGoogle Scholar
  23. Pears, N. E.: 2000, Feature extraction and tracking for scanning range sensors, Robotics and Autonomous Systems 33, 43–58.CrossRefGoogle Scholar
  24. Peña, J. M., Lozano, J. A. and Larrañaga, P.: 1995, An empirical comparison of four initialization methods for the K-means algorithm, Pattern Recognition Letters 20, 1027–1040.CrossRefGoogle Scholar
  25. Shpilman, R. and Brailovsky, V.: 1999, Fast and robust techniques for detecting straight line segments using local models, Pattern Recognition Letters 20(8), 865–877.CrossRefGoogle Scholar
  26. Siadat, A. and Dufaut, M.: 1998, Real time and dynamic local map building by using a 2D laser scanner, in: AVCS, pp. 307–312.Google Scholar
  27. Siadat, A., Kaske, A., Klausmann, S., Dufaut, M. and Husson, R.: 1997, An optimized segmentation method for a 2D laser-scanner applied to mobile robot navigation, in: 3rd IFAC Symp. on Intelligent Components and Instruments for Control Applications, France, pp. 153–158.Google Scholar
  28. Skrzypczynski, P.: 1995, Building geometrical map of environment using IR range finder data, in: Intelligent Autonomous Systems, pp. 408–412.Google Scholar
  29. Skrzypczynski, P.: 1997, Environment modelling using optical scanner data, in: IFAC Symposium on Robot Control, pp. 187–192.Google Scholar
  30. Vandorpe, J., van Brussel, H. and Xu, H.: 1996, Exact dynamic map building for a mobile robot using geometrical primitives produced by a 2D range finder, in: IEEE International Conference on Robotics and Automation, Minneapolis, MN, pp. 901–908.Google Scholar
  31. Young, T. Y. and Fu, K.-S.: 1986, Handbook of Pattern Recognition and Image Processing, Academic Press, London, U.K.Google Scholar
  32. Zhang, L. and Ghosh, B. K.: 2000, Line segment based map building and localization using 2D laser rangefinder, in: IEEE International Conference on Robotics and Automation, pp. 2538–2543.Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Geovany Araujo Borges
    • 1
  • Marie-José Aldon
    • 2
  1. 1.Electrical Engineering DepartmentUniversity of Brasilia (UnB)BrasiliaBrazil;
  2. 2.Robotics Department, LIRMM, UMR CNRS/Université Montpellier IIMontpellier Cedex 5France;

Personalised recommendations