Building Surface Refinement Using Cluster of Repeated Local Features by Cross Ratio

  • Hoang-Hon Trinh
  • Dae-Nyeon Kim
  • Kang-Hyun Jo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5027)


This paper describes an approach to recognize building surfaces. A building image is analyzed to extract the natural characters such as the surfaces and their areas, vanishing points, wall region and a list of SIFT feature vectors. These characters are organized as a hierarchical system of features to describe a model of building and then stored in a database. Given a new image, the characters are computed in the same form with in database. Then the new image is compared against the database to choose the best candidate. A cross ratio based algorithm, a novel approach, is used to verify the correct match. Finally, the correct match is used to update the model of building. The experiments show that the approach method clearly decreases the size of database, obtains high recognition rate. Furthermore, the problem of multiple buildings can be solved by separately analyzing each surface of building.


Repeated local feature recognition building surface cross ratio vanishing point 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Black, J., Jepsom, D.: Eigentracking: Robust Matching and Tracking of Articulated Objects Using a View-based Representation. IJCV 26(1), 63–84 (1998)CrossRefGoogle Scholar
  2. 2.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge Uni. Press, Cambridge (2004)zbMATHGoogle Scholar
  3. 3.
    Lowe, D.G.: Distinctive Image Features from Scale-invariant Keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  4. 4.
    Matas, J., Obdrzalek, S.: Object Recognition Methods based on Transformation Covariant Features. In: 12th European Signal Processing Conf. (2004)Google Scholar
  5. 5.
    Mikolajczyk, K., Schmid, C.: A Performance Evaluation of Local Descriptors. IEEE TPAMI 27(10) (October 2005)Google Scholar
  6. 6.
    Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints. IJCV 66(3), 231–259 (29) (2006)CrossRefGoogle Scholar
  7. 7.
    Schaffalitzky, F., Zisserman, A.: Multi-view Matching for Unordered Image Sets, or ’How Do I Organize My Holiday Snaps?’. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 414–431. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  8. 8.
    Shao, H., Gool, L.V.: Zubud-zurich Buildings Database for Image Based Recognition, Swiss FI of Tech., Tech. report no.260 (2003)Google Scholar
  9. 9.
    Swets, Weng, J.: Using Discriminant Eigenfeatures for Image Ietrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(8), 831–836 (1996)CrossRefGoogle Scholar
  10. 10.
    Trinh, H.H., Jo, K.H.: Image-based Structural Analysis of Building using Line Segments and their Geometrical Vanishing Points. In: SICE-ICASE, October 18-21 (2006)Google Scholar
  11. 11.
    Trinh, H.H., Kim, D.N., Jo, K.H.: Structure Analysis of Multiple Building for Mobile Robot Intelligence. In: SICE Proc., September 2007, Japan (2007)Google Scholar
  12. 12.
    Trinh, H.H., Kim, D.N., Jo, K.H.: Urban Building Detection and Analysis by Visual and Geometrical Features. In: ICCAS 2007, October 18-19, 2007, Seoul, Korea (2007)Google Scholar
  13. 13.
    Tuytelaars, T., Goedem, T., Van Gool, L.: Fast Wide Baseline Matching with Constrained Camera Position. In: CVPR, Washington, DC, pp. 24–29 (2004)Google Scholar
  14. 14.
    Zaboli, H., Rahmati, M.: An Improved Shock Graph Approach for Shape Recognition and Retrieval. In: Proceedings of the First Asia International Conference on Modelling & Simulation, pp. 438–443 (2007)Google Scholar
  15. 15.
    Zhang, W., Kosecka, J.: Hierarchical Building Recognition. In: IVC, May 2007, vol. 25, pp. 704–716. Daniel L. (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Hoang-Hon Trinh
    • 1
  • Dae-Nyeon Kim
    • 1
  • Kang-Hyun Jo
    • 1
  1. 1.Graduate School of Electrical EngineeringUniversity of Ulsan, KoreaUlsanKorea

Personalised recommendations