Advertisement

Detecting Keypoints with Stable Position, Orientation, and Scale under Illumination Changes

  • Bill Triggs
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3024)

Abstract

Local feature approaches to vision geometry and object recognition are based on selecting and matching sparse sets of visually salient image points, known as ‘keypoints’ or ‘points of interest’. Their performance depends critically on the accuracy and reliability with which corresponding keypoints can be found in subsequent images. Among the many existing keypoint selection criteria, the popular Förstner-Harris approach explicitly targets geometric stability, defining keypoints to be points that have locally maximal self-matching precision under translational least squares template matching. However, many applications require stability in orientation and scale as well as in position. Detecting translational keypoints and verifying orientation/scale behaviour post hoc is suboptimal, and can be misleading when different motion variables interact. We give a more principled formulation, based on extending the Förstner-Harris approach to general motion models and robust template matching. We also incorporate a simple local appearance model to ensure good resistance to the most common illumination variations. We illustrate the resulting methods and quantify their performance on test images.

Keywords

keypoint point of interest corner detection feature based vision Förstner-Harris detector template matching vision geometry object recognition 
Download to read the full conference paper text

References

  1. 1.
    Baker, S., Nayar, S., Murase, H.: Parametric feature detection. Int. J. Computer Vision 27(1), 27–50 (1998)CrossRefGoogle Scholar
  2. 2.
    Beaudet, P.R.: Rotationally invariant image operators. In: Int. Conf. Pattern Recognition, pp. 579–583 (1978)Google Scholar
  3. 3.
    Deriche, R., Blaszka, T.: Recovering and characterizing image features using an efficient model based approach. In: Int. Conf. ComputerVision & Pattern Recognition, pp. 530–535 (1993)Google Scholar
  4. 4.
    Deriche, R., Giraudon, G.: A computational approach for corner and vertex detection. Int. J. Computer Vision 10(2), 101–124 (1993)CrossRefGoogle Scholar
  5. 5.
    Faugeras, O., Luong, Q.-T., Papadopoulo, T.: The Geometry of Multiple Images. MIT Press, Cambridge (2001)zbMATHGoogle Scholar
  6. 6.
    Förstner, W.: On the geometric precision of digital correlation. Int. Arch. Photogrammetry & Remote Sensing 24(3), 176–189 (1982)Google Scholar
  7. 7.
    Förstner, W.: A feature-based correspondence algorithm for image matching. Int. Arch. Photogrammetry & Remote Sensing 26(3/3), 150–166 (1986)Google Scholar
  8. 8.
    Förstner, W.: A framework for low-level feature extraction. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 800, pp. II 383–394. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  9. 9.
    Förstner, W., Gülch, E.: A fast operator for detection and precise location of distinct points, corners and centres of circular features. In: ISPRS Intercommission Workshop, Interlaken (June 1987)Google Scholar
  10. 10.
    Grün, A.: Adaptive least squares correlation—concept and first results, March 1984. Intermediate Research Report to Helava Associates, p. 13. Ohio State University (1984)Google Scholar
  11. 11.
    Grün, A.: Least squares matching: A fundamental measurement algorithm. In: Close Range Photogrammetry and Machine Vision, pp. 217–255. Whittles Publishing, Caithness (1996)Google Scholar
  12. 12.
    Grün, A., Baltsavias, E.P.: Adaptive least squares correlation with geometrical constraints. In: SPIE Computer Vision for Robots, Cannes, vol. 595, pp. 72–82 (1985)Google Scholar
  13. 13.
    Hager, G., Belhumeur, P.: Efficient region tracking with parametric models of geometry and illumination. IEEE Trans. Pattern Analysis & Machine Intelligence 20(10), 1025–1039 (1998)CrossRefGoogle Scholar
  14. 14.
    Hannah, M.J.: Computer Matching of Areas in Stereo Images. Ph.D. Thesis, Stanford University, AIM Memo 219 (1974)Google Scholar
  15. 15.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  16. 16.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  17. 17.
    Kitchen, L., Rosenfeld, A.: Gray-level corner detection. Patt. Rec. Lett. 1, 95–102 (1982)CrossRefGoogle Scholar
  18. 18.
    Kovesi, P.: Image features from phase congruency. Videre: A Journal of Computer Vision Research 1(3) (1999)Google Scholar
  19. 19.
    Laganière, R.: Morphological corner detection. In: Int. Conf. Computer Vision, pp. 280–285 (1998)Google Scholar
  20. 20.
    Lowe, D.: Object recognition from local scale-invariant features. In: Int. Conf. Computer Vision, pp. 1150–1157 (1999)Google Scholar
  21. 21.
    Lowe, D.: Local feature view clustering for 3d object recognition. In: Int. Conf. Computer Vision & Pattern Recognition, pp. 682–688 (2001)Google Scholar
  22. 22.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI (1981)Google Scholar
  23. 23.
    Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: Int. Conf. Computer Vision, pp. 525–531 (2001)Google Scholar
  24. 24.
    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. I. 128–142. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  25. 25.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Int. Conf. Computer Vision & Pattern Recognition (2003)Google Scholar
  26. 26.
    Moravec, H.P.: Towards automatic visual obstacle avoidance. In: IJCAI, pp. 584 (1977)Google Scholar
  27. 27.
    Morrone, M.C., Owens, R.A.: Feature detection from local energy. Patt. Rec. Lett. 6, 303–313 (1987)CrossRefGoogle Scholar
  28. 28.
    Noble, J.A.: Finding corners. Image & Vision Computing 6(2), 121–128 (1988)CrossRefGoogle Scholar
  29. 29.
    Reisfeld, D.: The constrained phase congruency feature detector: Simultaneous localization, classification, and scale determination. Patt. Rec. Lett. 17, 1161–1169 (1996)CrossRefGoogle Scholar
  30. 30.
    Robbins, B., Owens, R.: 2d feature detection via local energy. Image &Vision Computing 15, 353–368 (1997)CrossRefGoogle Scholar
  31. 31.
    Rohr, K.: Localization properties of direct corner detectors. J. Mathematical Imaging & Vision 4(2), 139–150 (1994)CrossRefMathSciNetGoogle Scholar
  32. 32.
    Schaffalitzky, F., Zisserman, A.: Viewpoint invariant texture matching and wide baseline stereo. In: Int. Conf. Computer Vision, Vancouver, pp. 636–643 (2001)Google Scholar
  33. 33.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. Int. J. Computer Vision 37(2), 151–172 (2000)zbMATHCrossRefGoogle Scholar
  34. 34.
    Shi, J., Tomasi, C.: Good features to track. In: Int. Conf. Computer Vision & Pattern Recognition, Seattle, pp. 593–600 (1994)Google Scholar
  35. 35.
    Smith, S.M., Brady, J.M.: SUSAN - a new approach to low level image processing. Int. J. Computer Vision 23(1), 45–78 (1997)CrossRefGoogle Scholar
  36. 36.
    Toews, M., Arbel, T.: Entropy-of-likelihood feature selection for image correspondence. In: Int. Conf. Computer Vision, Nice, France, pp. 1041–1047 (2003)Google Scholar
  37. 37.
    Torr, P.H.S., Zisserman, A.: Feature based methods for structure and motion estimation. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) ICCV-WS 1999. LNCS, vol. 1883, pp. 278–294. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  38. 38.
    Zuniga, O., Haralick, R.: Corner detection using the facet model. In: Int. Conf. Computer Vision & Pattern Recognition, pp. 30–37 (1983)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Bill Triggs
    • 1
  1. 1.GRAVIR-CNRS-INRIAMontbonnotFrance

Personalised recommendations

Cite paper