Advertisement

Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions

  • Andrea Vedaldi
  • Stefano Soatto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)

Abstract

We study the set of domain deformations induced on images of three-dimensional scenes by changes of the vantage point. We parametrize such deformations and derive empirical statistics on the parameters, that show a kurtotic behavior similar to that of natural image and range statistics. Such a behavior would suggest that most deformations are locally smooth, and therefore could be captured by simple parametric maps, such as affine ones. However, we show that deformations induced by singularities and occluding boundaries, although rare, are highly salient, thus warranting the development of dedicated descriptors. We therefore illustrate the development of viewpoint invariant descriptors for singularities, as well as for occluding boundaries. We test their performance on scenes where the current state of the art based on affine-invariant region descriptors fail to establish correspondence, highlighting the features and shortcomings of our approach.

Keywords

Salient Region Region Descriptor Joint Histogram Domain Deformation Occlude Boundary 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 2, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  3. 3.
    Schaffalitzky, F., Zisserman, A.: Viewpoint invariant texture matching and wide baseline stereo. In: Proc. ICCV (2001)Google Scholar
  4. 4.
    Triggs, B.: Detecting keypoints with stable position, orientation, and scale under illumination changes. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 100–113. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  5. 5.
    Ullman, S., Vidal-Naquet, M., Sali, E.: Visual features of intermediate complexity and their use in classification. Nature 5 (2002)Google Scholar
  6. 6.
    Kadir, T., Brady, M.: Scale saliency: A novel approach to salient feature and scale selection. In: International Conference Visual Information Engineering (2003)Google Scholar
  7. 7.
    Lindeberg, T.: Feature detection with automatic scale selection. IJCV 30, 77–116 (1998)Google Scholar
  8. 8.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. BMVC (2002)Google Scholar
  9. 9.
    Fei-Fei, L., Fergus, R., Perona, P.: A Bayesian approach to unsupervised one-shot learning of object categories. In: Proc. ICCV (2003)Google Scholar
  10. 10.
    Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 18–32. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  11. 11.
    Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D object modeling and recognition using affine-invariant patches and multi-view spatial constraints. In: Proc. CVPR (2003)Google Scholar
  12. 12.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. CVPR (2003)Google Scholar
  13. 13.
    Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: Proc. ICCV (2003)Google Scholar
  14. 14.
    Ferrari, V., Tuytelaars, T., Van Gool, L.: Integrating multiple model views for object recognition. In: Proc. CVPR (2004)Google Scholar
  15. 15.
    Tuytelaars, T., Van Gool, L.: Wide baseline stereo matching based on local, affinely invariant regions. In: Proc. BMVC, pp. 412–425 (2000)Google Scholar
  16. 16.
    Dorkó, G., Schmid, C.: Object class recognition using discriminative local features. PAMI (submitted, 2004)Google Scholar
  17. 17.
    Fritz, G., Seifert, C., Paletta, L., Bischof, H.: Rapid object recognition from discriminative regions of interest. In: Proc. 19th National Conference on Artificial Intelligence, pp. 444–449 (2004)Google Scholar
  18. 18.
    Chen, H.F., Belhumeur, P.N., Jacobs, D.W.: In search of illumination invariants. In: Proc. CVPR (2000)Google Scholar
  19. 19.
    Guo, C., Zhu, S.C., Wu, Y.N.: Towards a mathematical theory of primal sketch and sketchability. In: Proc. ICCV, p. 1228 (2003)Google Scholar
  20. 20.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. IJCV 1, 63–86 (2004)CrossRefGoogle Scholar
  21. 21.
    Fergus, R., Perona, P., Zisserman, A.: A sparse object category model for efficient learning and exhaustive recognition. In: Proc. CVPR (2005)Google Scholar
  22. 22.
    Csurka, G., Dance, C.R., Dan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Proc. ECCV (2004)Google Scholar
  23. 23.
    Grauman, K., Darrell, T.: Efficient image matching with distributions of local invariant features. In: Proc. CVPR (2005)Google Scholar
  24. 24.
    Malik, J., Belongie, S., Shi, J., Leung, T.: Textons, contours and regions: Cue integration in image segmentation. In: Proc. CVPR (1999)Google Scholar
  25. 25.
    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
  26. 26.
    Ferrari, V., Tuytelaars, T., Van Gool, L.: Simultaneous object recognition and segmentation by image exploration. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 40–54. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  27. 27.
    Brown, M., Lowe, D.G.: Invariant features from interest point groups. In: Proc. BMVC (2002)Google Scholar
  28. 28.
    Fraundorfer, F., Bischof, H.: A novel performance evaluation method of local detectors on non-planar scenes. In: Proc. CVPR (2005)Google Scholar
  29. 29.
    Mikolajczyk, K., Zisserman, A., Schmid, C.: Shape recognition with edge-based features. In: Proc. BMVC (2003)Google Scholar
  30. 30.
    Stein, A., Hebert, M.: Incoporating background invariance into feature-based object recognition. In: Seventh IEEE Workshop on Applications of Computer Vision, WACV (2005)Google Scholar
  31. 31.
    Vasconcelos, N.: Feature selection by maximum marginal diversity: optimality and implications for visual recognition. In: Proc. CVPR (2003)Google Scholar
  32. 32.
    Wold, L., Shashua, A.: Feature selection for unsupervised and supervised inference: the emergence of sparsity in a weighted-based approach. In: Proc. ICCV (2003)Google Scholar
  33. 33.
    Levi, K., Weiss, Y.: Learning object detection from a small number of examples: the importance of good features. In: Proc. CVPR., vol. 2 (2004)Google Scholar
  34. 34.
    Grenander, U.: General Pattern Theory. Oxford University Press, Oxford (1993)Google Scholar
  35. 35.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models – their training and application. Comput. Vis. Image Underst. 61, 38–59 (1995)CrossRefGoogle Scholar
  36. 36.
    Huang, J., Lee, A.B., Mumford, D.: Statistics of range images. In: Proc. CVPR (2000)Google Scholar
  37. 37.
    Yang, Z., Purves, D.: Image/source statistics of surfaces in natural scenes. Network: Comput. in Neural Syst 14 (2003)Google Scholar
  38. 38.
    Roth, S., Black, M.J.: On the spatial statistics of optical flow. In: Proc. ICCV (2005)Google Scholar
  39. 39.
    Piqueres, J.V.: The persistence of ignorance (2006), http://www.ignorancia.org/
  40. 40.
    Meyer, M., Desbrun, M., Schröder, P., Barr, A.H.: Discrete differential geometry for triangulated 2-manifolds. In: Proc. of VisMath (2002)Google Scholar
  41. 41.
    Vedaldi, A., Soatto, S.: Features for recognition: Viewpoint invariance for non-planar scenes. In: Proc. ICCV (2005)Google Scholar
  42. 42.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Proceedings of The Fourth Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  43. 43.
    Bauer, J., Bischof, H., Klaus, A., Karner, K.: Robust and fully automated image registration using invariant features. In: Proc. of Intl. Arch. of Photogram., Remote Sensing and Sptl. Inf. Sci. (2004)Google Scholar
  44. 44.
    Lazebnik, S., Sethi, A., Schmid, C., Kriegman, D.J., Ponce, J., Hebert, M.: On pencils of tangent planes and the recognition of smooth 3D shapes from silhouettes. ICJV (2002)Google Scholar
  45. 45.
    Schmid, C., Zisserman, A.: The geometry and matching of curves in multiple views. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 394–409. Springer, Heidelberg (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Andrea Vedaldi
    • 1
  • Stefano Soatto
    • 1
  1. 1.University of California at Los AngelesLos AngelesUSA

Personalised recommendations