Journal of Intelligent & Robotic Systems

, Volume 63, Issue 1, pp 131–147 | Cite as

Spatial Modelling for Mobile Robot’s Vision-based Navigation

  • Dong-Young Yoo
  • Jin Young Choi
  • Jae-Kyu Lee
  • Seongjin Ahn
  • Jin Wook Chung


We present an algorithm to model 3D workspace and to understand test scene for mobile robot’s navigation or human computer interaction. This has done by line-based modeling and recognition algorithm. Line-based recognition using 3D lines has been tried by many researchers however its reliability still needs improvement due to ambiguity of 3D line feature information from original images. To improve the outcome, we approach firstly to find real planes using given 3D lines and then to implement recognition process. The methods we use are principle component analysis (PCA), plane sweep, occlusion query, and iterative closest point (ICP). During the implementation, we also use 3D map information for localization. We apply this algorithm to real test scene images and find out our result can be useful to identify doors or walls in indoor environment with better efficiency.


Line-based recognition Plane sweep Real plane Occlusion query Visibility test 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Schmid, C., Zisserman, A.: Automatic line matching across views. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 666–671 (1997)Google Scholar
  2. 2.
    Baillard, C., Zisserman, A., et al.: Automatic line matching and 3D reconstruction of buildings from multiple views. In: Conference on Automatic Extraction of GIS Objects from Digital Imagimary, Part 3-2W5, vol. 32, pp. 69–80 (2000)Google Scholar
  3. 3.
    Bignone, F., et al.: Automatic extraction of generic house roofs from high resolution aerial imagery. In: European Conference on Computer Vision, pp. 85–96 (1996)Google Scholar
  4. 4.
    Moons, T., et al.: Automatic modeling and 3D reconstruction of urban house roofs from high resolution aerial imagery. In: European Conference on Computer Vision, pp. 410–425 (1998)Google Scholar
  5. 5.
    Lee, S.C., Nevatia, R.: Interactive 3D building modeling using a hierarchical representation. In: IEEE Workshop on Higher-Level Knowledge in 3D Modeling and Motion in conjuction with International Conference on Computer Vision. Nice (2003)Google Scholar
  6. 6.
    Lee, S.C., Jung, S.K., Nevatia, R.: Automatic pose estimation of complex 3D building models. In: Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision (2002)Google Scholar
  7. 7.
    Criminisi, A., Reid, I., Zisserman, A.: A plane measuring device. In: Image Processing on British Machine Vision Conference (1997)Google Scholar
  8. 8.
    Baillard, C., Zisserman, A.: A plane-sweep strategy for the 3D reconstruction of buildings from multiple images. In: Proc. 19th. ISPRS Congress and Exhibition (2000)Google Scholar
  9. 9.
    Zhang, Z., Faugeras, O.: Determining motion from 3D line segment matches: a comparative study. Image Vis. Comput. 9(1) 10–19 (1991)CrossRefGoogle Scholar
  10. 10.
    Chen, Y., Medioni, G.: Object modeling by registration of multiple range images. In: IEEE International Conference on Robotics and Automation, pp. 2724–2729 (1991)Google Scholar
  11. 11.
    Besl, P., MaKay, N.: A method for registration of 3-D shapes. IEEE Pattern Anal. Mach. Intell. 14(2), 239–256 (1992)CrossRefGoogle Scholar
  12. 12.
    Kamgar-Parsi, B., Kamgar-Parsi, B.: Algorithms for matching 3D line sets. IEEE Pattern Anal. Mach. Intell. 26(5), 582–593 (2004)CrossRefGoogle Scholar
  13. 13.
    Guerra, C., Pascucci, V.: Line-based object recognition using Hausdorff distance: from range images to molecular secondary structures. Image Vis. Comput. 23(4), 405–415 (2005)CrossRefGoogle Scholar
  14. 14.
    Lee, S., Lee, S., Lee, J., Moon, D., Kim, E., Seo, J.: Robust recognition and pose estimation of 3D objects based on evidence fusion in a sequence of images. In: IEEE International Conference on Robotics and Automation (2007)Google Scholar
  15. 15.
    Boissonnat, J.D., Snoeyink, J.: Efficient algorithms for line and curve segment intersection using restricted predicates. In: 15th Annual ACM Symposium of Computational Geometry, pp. 370–379 (1999)Google Scholar
  16. 16.
    Balaban, I.: An optimal algorithm for finding segment intersections. In: Proceedings, 11th Annual ACM Symposium of Computational Geometry, pp. 211–219 (1995)Google Scholar
  17. 17.
    Bartuschka, U., Mehlhorn, K., Naher, S.: A robust and efficient implementation of a sweep line algorithm for the straight line segment intersection problem. In: Proceedings, Workshop on Algorithm Engineering, pp. 124–135 (1997)Google Scholar
  18. 18.
    Bentley, J.L., Ottoman, T.A.: Algorithm for reporting and counting geometric intersections. IEEE Trans. Comput. C-28(9), 643–647 (1979)CrossRefGoogle Scholar
  19. 19.
    Boissonnat, J.D., Preparata, F.P.: Robust plane sweep for intersecting segments. SIAM J. Comput. 29(5), 1401–1421 (2000)MathSciNetMATHCrossRefGoogle Scholar
  20. 20.
    Palazzi, L., Snoeyink, J.: Counting and reporting red/blue segment intersections. CVGIP, Graph. Models Image Process. 56(4), 304–311 (1994)CrossRefGoogle Scholar
  21. 21.
    Cohen-Or, S., Chrysanthou, Y., Silva, C.T., Durand, F.: A survey of visibility for walkthrough applications. IEEE Trans. Vis. Comput. Graph. 9(3), 412–432 (2003)CrossRefGoogle Scholar
  22. 22.
    Ben-Arie, J.: The probabilistic peaking effect of viewed angles and distances with application to 3-D object recognition. IEEE Trans. Pattern Anal. Mach. Intell. 12(8), 760–774 (1990)CrossRefGoogle Scholar
  23. 23.
    Stein, F., Medioni, G.: Structural indexing: efficient 3D object recognition. IEEE Trans. Pattern Anal. Mach. Intell. 14(2), 125–145 (1992)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  • Dong-Young Yoo
    • 1
  • Jin Young Choi
    • 2
  • Jae-Kyu Lee
    • 3
  • Seongjin Ahn
    • 4
  • Jin Wook Chung
    • 3
  1. 1.Korea Internet and Security AgencySeoulSouth Korea
  2. 2.Korea UniversitySeoulRepublic of Korea
  3. 3.Sungkyunkwan UniversitySuwonSouth Korea
  4. 4.Sungkyunkwan UniversitySeoulSouth Korea

Personalised recommendations