Object Detection by Keygraph Classification

  • Marcelo Hashimoto
  • Roberto M. CesarJr.
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5534)


In this paper, we propose a new approach for keypoint-based object detection. Traditional keypoint-based methods consist of classifying individual points and using pose estimation to discard misclassifications. Since a single point carries no relational features, such methods inherently restrict the usage of structural information. Therefore, the classifier considers mostly appearance-based feature vectors, thus requiring computationally expensive feature extraction or complex probabilistic modelling to achieve satisfactory robustness. In contrast, our approach consists of classifying graphs of keypoints, which incorporates structural information during the classification phase and allows the extraction of simpler feature vectors that are naturally robust. In the present work, 3-vertices graphs have been considered, though the methodology is general and larger order graphs may be adopted. Successful experimental results obtained for real-time object detection in video sequences are reported.


Feature Vector IEEE Computer Society Object Detection Delaunay Triangulation Internal Angle 
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.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 20, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Bay, H., Tuytelaars, T., van Gool, L.: SURF: Speeded Up Robust Features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  3. 3.
    Lepetit, V., Fua, P.: Keypoint recognition using randomized trees. IEEE Transactions on Pattern Analysis and Machine Inteligence 28, 1465–1479 (2006)CrossRefGoogle Scholar
  4. 4.
    Özuysal, M., Fua, P., Lepetit, V.: Fast keypoint recognition in ten lines of code. In: Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE Computer Society, Los Alamitos (2007)Google Scholar
  5. 5.
    Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. IEEE Transactions on Pattern Analysis and Machine Inteligence 19, 530–535 (1997)CrossRefGoogle Scholar
  6. 6.
    Tell, D., Carlsson, S.: Combining appearance and topology for wide baseline matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 68–81. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  7. 7.
    Tang, F., Tao, H.: Object tracking with dynamic feature graph. In: Proceedings of the 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pp. 25–32. IEEE Computer Society, Los Alamitos (2005)Google Scholar
  8. 8.
  9. 9.
    Shi, J., Tomasi, C.: Good features to track. In: Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 593–600. IEEE Computer Society, Los Alamitos (1994)Google Scholar
  10. 10.
    Fortune, S.: A sweepline algorithm for Voronoi diagrams. In: Proceedings of the Second Annual Symposium on Computational Geometry, pp. 313–322. ACM, New York (1986)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Marcelo Hashimoto
    • 1
  • Roberto M. CesarJr.
    • 1
  1. 1.Instituto de Matemática e Estatística - IMEUniversidade de São Paulo - USPSão PauloBrazil

Personalised recommendations