Advertisement

International Journal of Computer Vision

, Volume 73, Issue 3, pp 263–284 | Cite as

Evaluation of Features Detectors and Descriptors based on 3D Objects

  • Pierre Moreels
  • Pietro Perona
Article

Abstract

We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. These correspondences are based purely on geometric information, and do not rely on the choice of a specific feature appearance descriptor. We test detector-descriptor combinations on a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. We find that the combination of Hessian-affine feature finder and SIFT features is most robust to viewpoint change. Harris-affine combined with SIFT and Hessian-affine combined with shape context descriptors were best respectively for lighting change and change in camera focal length. We also find that no detector-descriptor combination performs well with viewpoint changes of more than 25–30.

Keywords

features detectors features descriptors object recognition 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ballester, C. and Gonzalez, M. 1998. Affine invariant texture segmentation and shape from texture by variational methods. Journal of Mathematical Imaging and Vision, 9:141–171.CrossRefMathSciNetzbMATHGoogle Scholar
  2. Beaudet, P.R. 1978. Rotationally invariant image operators. In International Joint Conference on Pattern Recognition, Kyoto, Japan, pp. 579–583.Google Scholar
  3. Belongie, S., Malik, J., and Puzicha, J. 2002. Shape matching and object recognition using shape contexts. In IEEE Transactions on Pattern Analysis and Machine Intelligence.Google Scholar
  4. Bouguet, J.Y. 1999. Visual methods for three-dimensional modeling. PhD thesis, Caltech.Google Scholar
  5. Brown, M. and Lowe, D.G. 2003. Recognising panoramas. In International Conference on Computer Vision.Google Scholar
  6. Carneiro, G. and Jepson, A.D. 2004. Flexible spatial models for grouping local image features. In IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
  7. Crowley, J.L. and Parker, A.C. 1984. A representation for shape based on peaks and ridges in the difference of low-pass transform. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6:156–168.CrossRefGoogle Scholar
  8. Forstner, W. 1986. A feature based correspondence algorithms for image matching. Intl. Arch. Photogrammetry and Remote Sensing, 24:60–166.Google Scholar
  9. Fraundorfer, F. and Bischof, H. 2004. Evaluation of local detectors on non-planar scenes. OAGM/AAPR workshop, Austrian Association for Pattern Recognition.Google Scholar
  10. Freeman, W. and Adelson, E. 1991. The design and use of steerable filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(9):891–906.CrossRefGoogle Scholar
  11. Harris, C. and Stephens, M. 1988. A combined corner and edge detector. In Alvey Vision Conference, pp. 147–151.Google Scholar
  12. Hartley, R. and Zisserman, A. 2000. Multiple view geometry in computer vision. Cambridge editor.Google Scholar
  13. Kadir, T., Zisserman, A., and Brady, M. 2004. An affine invariant salient Region Detector. In European Conference on Computer Vision, pp. 228–241.Google Scholar
  14. Ke, Y. and Sukthankar, R. 2004. PCA-SIFT: A more distinctive representation for local image descriptors. In IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
  15. Leibe, B., Seemann, E., and Schiele, B. 2005. Pedestrian detection in crowded scenes”. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 878–885.Google Scholar
  16. Lindeberg, T. 1994. Scale-space theory: A basic tool for analising structures at different scales. Journal of Applied Statistics, 21(2):225–270.Google Scholar
  17. Lindeberg, T. 1998. Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2):79–116.CrossRefGoogle Scholar
  18. Lucas, B.D. and Kanade, T. 1981. An iterative image registration technique with an application to stereo vision. In 7th International Joint Conference on Artificial Intelligence, pp. 674–679.Google Scholar
  19. Lindeberg, T. and Garding, J. 1997. Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure. Image and Vision Computing, 15(6):415–434.CrossRefGoogle Scholar
  20. Lowe, D.G. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2):91–110.CrossRefGoogle Scholar
  21. Matas, J., Chum, O., Urban, M., and Pajdla, T. 2002. Robust wide baseline stereo from maximally stable extremal regions. British Machine Vision Conference, 384–393.Google Scholar
  22. Mikolajczyk, K. and Schmid, C. 2002. An affine invariant interest point detector. European Conference on Computer Vision.Google Scholar
  23. Mikolajczyk, K. et al. 2004. A comparison of affine region detectors. International Journal of Computer Vision (submitted).Google Scholar
  24. Mikolajczyk, K., Leibe, B., and Schiele, B. 2005. Local features for object class recognition. In International Conference on Computer Vision.Google Scholar
  25. Mikolajczyk, K. and Schmid, C. A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence (To appear).Google Scholar
  26. Moreels, P. and Perona, P. 2004. Common-frame model for object recognition. In Neural Information Processing Systems.Google Scholar
  27. Moreels, P. and Perona, P. 2005a. Evaluation of features detectors and descriptors based on 3D objects. In International Conference on Computer Vision.Google Scholar
  28. Moreels, P. and Perona, P. 2005b. Probabilistic coarse-to-fine object recognition. Technical report.Google Scholar
  29. Schaffalitzky, F. and Zisserman, A. 2001. Viewpoint invariant texture matching and wide baseline stereo. In International Conference on Computer Vision, pp. 636–643.Google Scholar
  30. Schmid, C. and Mohr, R. 1997. Local greyvalue invariants for image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(5):530–535.CrossRefGoogle Scholar
  31. Schmid, C., Mohr, R., and Bauckhage, C. 2000. Evaluation of interest point detectors. International Journal of Computer Vision, 37(2):151–172.CrossRefzbMATHGoogle Scholar
  32. Se, S., Lowe, D.G., and Little, J. 2002. Mobile robot localization and mapping with uncertainty using scale-invariant visual landmarks. International Journal of Robotics Research, 21(8):735–738.CrossRefGoogle Scholar
  33. Semple, J.G. and Kneebone, G.T. 1952. Algebraic Projective Geometry. Oxford Science Publication.Google Scholar
  34. Shashua, A. and Werman, M. 1995. On the trilinear tensor of three perspective views and its underlying geomtry. International Conference on Computer Vision.Google Scholar
  35. Shi, J. and Tomasi, C. 1994. Good features to track. IEEE Conference on Computer Vision and Pattern Recognition, Seattle.Google Scholar
  36. Tuytelaars, T. and Van Gool, L. 2000. Wide baseline stereo matching based on local affinely invariant regions. In British Machine Vision Conference.Google Scholar
  37. Tuytelaars, T. and Van Gool, L. 2004. Matching widely separated views based on affine invariant regions. International Journal on Computer Vision, 59(1):61–85.CrossRefGoogle Scholar
  38. van Vliet, L.J., Young, I.T., and Verbeek, P.W. 1998. Recursive gaussian derivative filters. In International Conference on Pattern Recognition, pp. 509–514.Google Scholar
  39. Vincent, L. and Soille, P. 1991. Watersheds in digital spaces: an efficient algorithm based on immersion simulations. In IEEE Transactions on Pattern Analysis and Machine Intelligence.Google Scholar

Copyright information

© Springer Science + Business Media, LLC 2006

Authors and Affiliations

  1. 1.California Institute of TechnologyPasadenaUSA

Personalised recommendations