Machine Learning for High-Speed Corner Detection

  • Edward Rosten
  • Tom Drummond
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3951)

Abstract

Where feature points are used in real-time frame-rate applications, a high-speed feature detector is necessary. Feature detectors such as SIFT (DoG), Harris and SUSAN are good methods which yield high quality features, however they are too computationally intensive for use in real-time applications of any complexity. Here we show that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time. By comparison neither the Harris detector (120%) nor the detection stage of SIFT (300%) can operate at full frame rate.

Clearly a high-speed detector is of limited use if the features produced are unsuitable for downstream processing. In particular, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations [1]. Hence the second contribution of this paper is a comparison corner detectors based on this criterion applied to 3D scenes. This comparison supports a number of claims made elsewhere concerning existing corner detectors. Further, contrary to our initial expectations, we show that despite being principally constructed for speed, our detector significantly outperforms existing feature detectors according to this criterion.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. International Journal of Computer Vision 37, 151–172 (2000)CrossRefMATHGoogle Scholar
  2. 2.
    Rosten, E., Drummond, T.: Fusing points and lines for high performance tracking. In: 10th IEEE International Conference on Computer Vision, Beijing, China, vol. 2, pp. 1508–1515. Springer, Heidelberg (2005)Google Scholar
  3. 3.
    Rosten, E., Reitmayr, G., Drummond, T.: Real-time video annotations for augmented reality. In: International Symposium on Visual Computing (2005)Google Scholar
  4. 4.
    Moravec, H.: Obstacle avoidance and navigation in the real world by a seeing robot rover. In: Tech. report CMU-RI-TR-80-03, Robotics Institute, Carnegie Mellon University & doctoral dissertation, Stanford University. Carnegie Mellon University (1980); available as Stanford AIM-340, CS-80-813 and republished as a Carnegie Mellon University Robotics Institue Technical Report to increase availabilityGoogle Scholar
  5. 5.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  6. 6.
    Noble, J.A.: Finding corners. Image and Vision Computing 6, 121–128 (1988)CrossRefGoogle Scholar
  7. 7.
    Shi, J., Tomasi, C.: Good features to track. In: 9th IEEE Conference on Computer Vision and Pattern Recognition, Springer, Heidelberg (1994)Google Scholar
  8. 8.
    Noble, A.: Descriptions of image surfaces. PhD thesis, Department of Engineering Science, University of Oxford (1989)Google Scholar
  9. 9.
    Kenney, C.S., Manjunath, B.S., Zuliani, M., Hewer, M.G.A., Nevel, A.V.: A condition number for point matching with application to registration and postregistration error estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 1437–1454 (2003)CrossRefGoogle Scholar
  10. 10.
    Zuliani, M., Kenney, C., Manjunath, B.: A mathematical comparison of point detectors. In: Second IEEE Image and Video Registration Workshop (IVR), Washington DC, USA (2004)Google Scholar
  11. 11.
    Zheng, Z., Wang, H., Teoh, E.K.: Analysis of gray level corner detection. Pattern Recognition Letters 20, 149–162 (1999)CrossRefMATHGoogle Scholar
  12. 12.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  13. 13.
    James, L., Crowley, O.R.: Fast computation of characteristic scale using a half octave pyramid. In: Scale Space 2003: 4th International Conference on Scale-Space theories in Computer Vision, Isle of Skye, Scotland (2003)Google Scholar
  14. 14.
    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
  15. 15.
    Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: 8th IEEE International Conference on Computer Vision, Vancouver, Canada, Springer, pp. 525–531 (2001)Google Scholar
  16. 16.
    Brown, M., Lowe, D.G.: Invariant features from interest point groups. In: 13th British Machine Vision Conference, Cardiff, British Machine Vision Assosciation, pp. 656–665 (2002)Google Scholar
  17. 17.
    Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets, or how do I organize my holiday snaps? In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 414–431. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  18. 18.
    Rutkowski, W.S., Rosenfeld, A.: A comparison of corner detection techniques for chain coded curves. Technical Report 623, Maryland University (1978)Google Scholar
  19. 19.
    Langridge, D.J.: Curve encoding and detection of discontinuities. Computer Vision, Graphics and Image Processing 20, 58–71 (1987)CrossRefGoogle Scholar
  20. 20.
    Medioni, G., Yasumoto, Y.: Corner detection and curve representation using cubic b-splines. Computer Vision, Graphics and Image Processing 39, 279–290 (1987)CrossRefMATHGoogle Scholar
  21. 21.
    Mokhtarian, F., Suomela, R.: Robust image corner detection through curvature scale space. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 1376–1381 (1998)CrossRefGoogle Scholar
  22. 22.
    Haralick, R.M., Shapiro, L.G.: Computer and robot vision, vol. 1. Addison-Wesley, Reading (1993)Google Scholar
  23. 23.
    Cooper, J., Venkatesh, S., Kitchen, L.: Early jump-out corner detectors. IEEE Transactions on Pattern Analysis and Machine Intelligence 15, 823–828 (1993)CrossRefGoogle Scholar
  24. 24.
    Wang, H., Brady, M.: Real-time corner detection algorithm for motion estimation. Image and Vision Computing 13, 695–703 (1995)CrossRefGoogle Scholar
  25. 25.
    Kitchen, L., Rosenfeld, A.: Gray-level corner detection. Pattern Recognition Letters 1, 95–102 (1982)CrossRefGoogle Scholar
  26. 26.
    Guiducci, A.: Corner characterization by differential geometry techniques. Pattern Recognition Letters 8, 311–318 (1988)CrossRefMATHGoogle Scholar
  27. 27.
    Smith, S.M., Brady, J.M.: SUSAN - a new approach to low level image processing. International Journal of Computer Vision 23, 45–78 (1997)CrossRefGoogle Scholar
  28. 28.
    Trajkovic, M., Hedley, M.: Fast corner detection. Image and Vision Computing 16, 75–87 (1998)CrossRefGoogle Scholar
  29. 29.
    Loy, G., Zelinsky, A.: A fast radial symmetry transform for detecting points of interest. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 358–368. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  30. 30.
    Dias, P., Kassim, A., Srinivasan, V.: A neural network based corner detection method. In: IEEE International Conference on Neural Networks, Perth, WA, Australia, vol. 4, pp. 2116–2120 (1995)Google Scholar
  31. 31.
    Quinlan, J.R.: Induction of decision trees. Machine Learning 1, 81–106 (1986)Google Scholar
  32. 32.
  33. 33.
    Performenace Evaluation of Corner Detection Algorithms under Affine and Similarity Transforms. In: Cootes, T.F., Taylor, C. (eds.) 12th British Machine Vision Conference, Manchester, British Machine Vision Assosciation (2001)Google Scholar
  34. 34.
    Schmid, C., Mohr, R., Bauckhage, C.: Comparing and evaluating interest points. In: 6th IEEE International Conference on Computer Vision, Bombay, India, pp. 230–235. Springer, Heidelberg (1998)Google Scholar
  35. 35.
    Lowe, D.G.: Demo software: Sift keypoint detector (accessed 2005), http://www.cs.ubc.ca/~lowe/keypoints/
  36. 36.
    Sklar, B.: Digital Communications. Prentice-Hall, Englewood Cliffs (1988)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Edward Rosten
    • 1
  • Tom Drummond
    • 1
  1. 1.Department of EngineeringCambridge UniversityUK

Personalised recommendations