A Boundary-Fragment-Model for Object Detection

  • Andreas Opelt
  • Axel Pinz
  • Andrew Zisserman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)


The objective of this work is the detection of object classes, such as airplanes or horses. Instead of using a model based on salient image fragments, we show that object class detection is also possible using only the object’s boundary. To this end, we develop a novel learning technique to extract class-discriminative boundary fragments. In addition to their shape, these “codebook” entries also determine the object’s centroid (in the manner of Leibe et al. [19]). Boosting is used to select discriminative combinations of boundary fragments (weak detectors) to form a strong “Boundary-Fragment-Model” (BFM) detector. The generative aspect of the model is used to determine an approximate segmentation.

We demonstrate the following results: (i) the BFM detector is able to represent and detect object classes principally defined by their shape, rather than their appearance; and (ii) in comparison with other published results on several object classes (airplanes, cars-rear, cows) the BFM detector is able to exceed previous performances, and to achieve this with less supervision (such as the number of training images).


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE PAMI 26(11), 1475–1490 (2004)CrossRefGoogle Scholar
  2. 2.
    Amores, J., Sebe, N., Radeva, P.: Fast spatial pattern discovery integrating boosting with constellations of contextual descriptors. In: Proc. CVPR, CA, USA, June 2005, vol. 2, pp. 769–774 (2005)Google Scholar
  3. 3.
    Bar-Hillel, A., Hertz, T., Weinshall, D.: Object class recognition by boosting a part-based model. In: Proc. CVPR, June 2005, vol. 2, pp. 702–709 (2005)Google Scholar
  4. 4.
    Bernstein, E.J., Amit, Y.: Part-based statistical models for object classification and detection. In: Proc. CVPR, vol. 2, pp. 734–740 (2005)Google Scholar
  5. 5.
    Borgefors, G.: Hierarchical chamfer matching: A parametric edge matching algorithm. IEEE PAMI 10(6), 849–865 (1988)CrossRefGoogle Scholar
  6. 6.
    Breu, H., Gil, J., Kirkpatrick, D., Werman, M.: Linear time Euclidean distance transform algorithms. IEEE PAMI 17(5), 529–533 (1995)CrossRefGoogle Scholar
  7. 7.
    Caputo, B., Wallraven, C., Nilsback, M.: Object categorization via local kernels. In: Proc. ICPR, pp. 132–135 (2004)Google Scholar
  8. 8.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach towards feature space analysis. IEEE PAMI 24(5), 603–619 (2002)CrossRefGoogle Scholar
  9. 9.
    Crandall, D., Felzenszwalb, P., Huttenlocher, D.: Spatial priors for part-based recognition using statistical models. In: Proc. CVPR, pp. 10–17 (2005)Google Scholar
  10. 10.
    Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: ECCV 2004. Workshop on Stat. Learning in Computer Vision, pp. 59–74 (2004)Google Scholar
  11. 11.
    Felzenszwalb, P., Huttenlocher, D.: Pictorial structures for object recognition. Intl. Journal of Computer Vision 61(1), 55–79 (2004)CrossRefGoogle Scholar
  12. 12.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. CVPR, pp. 264–271 (2003)Google Scholar
  13. 13.
    Fergus, R., Perona, P., Zisserman, A.: A visual category filter for google images. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 242–256. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  14. 14.
    Fergus, R., Perona, P., Zisserman, A.: A sparse object category model for efficient learning and exhaustive recognition. In: Proc. CVPR (2005)Google Scholar
  15. 15.
    Freund, Y., Schapire, R.: A decision theoretic generalisation of online learning. Computer and System Sciences 55(1), 119–139 (1997)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Jurie, F., Schmid, C.: Scale-invariant shape features for recognition of object categories. In: Proc. of CVPR, pp. 90–96 (2004)Google Scholar
  17. 17.
    Kumar, M., Torr, P., Zisserman, A.: Extending pictural structures for object recognition. In: Proc. BMVC (2004)Google Scholar
  18. 18.
    Leibe, B.: Interleaved Object Categorization and Segmentation. PhD thesis, Swiss Federal Institute of Technology (2004)Google Scholar
  19. 19.
    Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: ECCV 2004. Workshop on Stat. Learning in Computer Vision, May 2004, pp. 17–32 (2004)Google Scholar
  20. 20.
    Leibe, B., Schiele, B.: Scale-invariant object categorization using a scale-adaptive mean-shift search. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 145–153. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  21. 21.
    Magee, D., Boyle, R.: Detecting lameness using re-sampling condensation and multi-steam cyclic hidden markov models. Image and Vision Computing 20(8), 581–594 (2002)CrossRefGoogle Scholar
  22. 22.
    Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: Weak hypotheses and boosting for generic object detection and recognition. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 71–84. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  23. 23.
    Sali, E., Ullman, S.: Combining class-specific fragments for object classification. In: Proc. BMVC, pp. 203–213 (1999)Google Scholar
  24. 24.
    Shotton, J., Blake, A., Cipolla, R.: Contour-based learning for object detection. In: Proc. ICCV, pp. 503–510 (2005)Google Scholar
  25. 25.
    Sivic, J., Russell, B., Efros, A., Zisserman, A., Freeman, W.: Discovering objects and their location in images. In: Proc. ICCV (2005)Google Scholar
  26. 26.
    Thureson, J., Carlsson, S.: Appearance based qualitative image description for object class recognition. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 518–529. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  27. 27.
    Vidal-Naquet, M., Ullman, S.: Object recognition with informative features and linear classification. In: Proc. ICCV, vol. 1, pp. 281–288 (2003)Google Scholar
  28. 28.
    Zhang, W., Yu, B., Zelinsky, G., Samaras, D.: Object class recognition using multiple layer boosting with heterogenous features. In: Proc. CVPR, pp. 323–330 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Andreas Opelt
    • 1
  • Axel Pinz
    • 1
  • Andrew Zisserman
    • 2
  1. 1.Vision-based Measurement Group, Inst. of El. Measurement and Meas. Sign. Proc.University of TechnologyGrazAustria
  2. 2.Visual Geometry Group, Department of Engineering ScienceUniversity of OxfordUK

Personalised recommendations