Real-Time Model-Based SLAM Using Line Segments

  • Andrew P. Gee
  • Walterio Mayol-Cuevas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4292)


Existing monocular vision-based SLAM systems favour interest point features as landmarks, but these are easily occluded and can only be reliably matched over a narrow range of viewpoints. Line segments offer an interesting alternative, as line matching is more stable with respect to viewpoint changes and lines are robust to partial occlusion. In this paper we present a model-based SLAM system that uses 3D line segments as landmarks. Unscented Kalman filters are used to initialise new line segments and generate a 3D wireframe model of the scene that can be tracked with a robust model-based tracking algorithm. Uncertainties in the camera position are fed into the initialisation of new model edges. Results show the system operating in real-time with resilience to partial occlusion. The maps of line segments generated during the SLAM process are physically meaningful and their structure is measured against the true 3D structure of the scene.


Line Segment Unscented Kalman Filter Partial Occlusion Edge Feature Model Edge 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Davison, A.J.: Real-time simultaneous localisation and mapping with a single camera. In: Proc. of the Int. Conf. on Computer Vision (2003)Google Scholar
  2. 2.
    Shi, J., Tomasi, C.: Good features to track. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 593–600 (1994)Google Scholar
  3. 3.
    Molton, N.D., Davison, A.J., Reid, I.D.: Locally planar patch features for real-time structure from motion. In: Proc. of the British Machine Vision Conference (2004)Google Scholar
  4. 4.
    Pupilli, M., Calway, A.: Real-time visual slam with resilience to erratic motion. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (2006)Google Scholar
  5. 5.
    Eade, E., Drummond, T.: Scalable monocular slam. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (2006)Google Scholar
  6. 6.
    Lemaire, T., Lacroix, S.: Monocular-vision based SLAM using line segments. Technical report, LAAS-CNRS (2006) (submitted to IROS 2006)Google Scholar
  7. 7.
    Harris, C.: Tracking with rigid models. Active Vision, 59–73 (1992)Google Scholar
  8. 8.
    Armstrong, M., Zisserman, A.: Robust object tracking. In: Proc. of the Asian Conf. on Computer Vision, pp. 58–62 (1995)Google Scholar
  9. 9.
    Drummond, T., Cipolla, R.: Real-time visual tracking of complex structures. IEEE Trans. on Pattern Analysis and Machine Intelligence 24, 932–946 (2002)CrossRefGoogle Scholar
  10. 10.
    Comport, A.I., Marchand, E., Pressigout, M., Chaumette, F.: Real-time markerless tracking for augmented reality: the virtual visual servoing framework. IEEE Trans. on Visualization and Computer Graphics 12 (2006)Google Scholar
  11. 11.
    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM 24, 381–395 (1981)CrossRefMathSciNetGoogle Scholar
  12. 12.
    Comport, A.I., Kragic, D., Marchand, E., Chaumette, F.: Robust real-time visual tracking: Comparison, theoretical analysis and performance evaluation. In: Proc. of the IEEE Int. Conf. on Robotics and Automation, pp. 2852–2857 (2005)Google Scholar
  13. 13.
    Julier, S., Uhlmann, J.: A new extension of the kalman filter to nonlinear systems. In: Int. Symp. on Aerospace/Defense Sensing, Simulation and Controls (1997)Google Scholar
  14. 14.
    Gates, J., Haseyama, M., Kitajima, H.: A new conic section extraction approach and its applications. IEICE Trans. on Info. and Sys. 88-D, 239–251 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Andrew P. Gee
    • 1
  • Walterio Mayol-Cuevas
    • 1
  1. 1.Department of Computer ScienceUniversity of BristolUK

Personalised recommendations