HARMONIC DEFORMATION MODEL FOR EDGE BASED TEMPLATE MATCHING

Andreas Hofhauser, Carsten Steger, Nassir Navab

2008

Abstract

The paper presents an approach to the detection of deformable objects in single images. To this end we propose a robust match metric that preserves the relative edge point neighborhood, but allows significant shape changes. Similar metrics have been used for the detection of rigid objects (Olson and Huttenlocher, 1997; Steger, 2002). To the best of our knowledge this adaptation to deformable objects is new. In addition, we present a fast algorithm for model deformation. In contrast to the widely used thin-plate spline (Bookstein, 1989; Donato and Belongie, 2002), it is efficient even for several thousand points. For arbitrary deformations, a forward-backward interpolation scheme is utilized. It is based on harmonic inpainting, i.e. it regularizes the displacement in order to obtain smooth deformations. Similar to optical flow, we obtain a dense deformation field, though the template contains only a sparse set of model points. Using a coarse-to-fine representation for the distortion of the template further increases efficiency. We show in a number of experiments that the presented approach in not only fast, but also very robust in detecting deformable objects.

References

  1. Aubert, G. and Kornprobst, P. (2006). Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations (second edition), volume 147 of Applied Mathematical Sciences. Springer-Verlag.
  2. Bay, H., Tuytelaars, T., and Gool, L. V. (2006). Surf: Speeded up robust features. European Conference on Computer Vision.
  3. Belongie, S., Malik, J., and Puzicha, J. (2002). Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(4):509-522.
  4. Berg, A., Berg, T., and Malik, J. (2005). Shape matching and object recognition using low distortion correspondences. In Conference on Computer Vision and Pattern Recognition, San Diego, CA.
  5. Bookstein, F. L. (1989). Principal warps: Thin plate splines and the decomposition of deformations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11:567-585.
  6. Donato, G. and Belongie, S. (2002). Approximate thin plate spline mappings. European Conference on Computer Vision, 2:531-542.
  7. Felzenszwalb, P. F. (2003). Representation and detection of deformable shapes. In Computer Vision and Pattern Recognition, volume 1, pages 102-108.
  8. Gavrila, D. M. and Philomin, V. (1999). Real-time object detection for “smart” vehicles. In 7th International Conference on Computer Vision, volume I, pages 87- 93.
  9. Gonzales-Linares, J., N.Guil, and E.L.Zapata (2003). An efficient 2d deformable object detection and location algorithm. In Pattern Recognition, volume 36, pages 2543-2556.
  10. Horn, B. K. P. and Schunck, B. G. (1981). Determining optical flow. Artifical Intelligence, 17:185-203.
  11. Jain, A. K., Zhong, Y., and Lakshmanan, S. (1996). Object matching using deformable templates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(3):267-278.
  12. Lepetit, V., Lagger, P., and Fua, P. (2005). Randomized trees for real-time keypoint recognition. In Conference on Computer Vision and Pattern Recognition, San Diego, CA.
  13. Lowe, D. G. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision.
  14. Modersitzki, J. (2004). Numerical Methods for Image Registration. Oxford University Press Series: Numerical Mathematics and Scientific Computation.
  15. Olson, C. F. and Huttenlocher, D. P. (1997). Automatic target recognition by matching oriented edge pixels. IEEE Transactions on Image Processing, 6(1):103- 113.
  16. Pilet, J., Lepetit, V., and Fua, P. (2005). Real-time non-rigid surface detection. In Conference on Computer Vision and Pattern Recognition, San Diego, CA.
  17. Steger, C. (2002). Occlusion, clutter, and illumination invariant object recognition. In Kalliany, R. and Leberl, F., editors, International Archives of Photogrammetry, Remote Sensing, and Spatial Information Sciences, volume XXXIV, part 3A, pages 345-350, Graz.
  18. Ulrich, M., Baumgartner, A., and Steger, C. (2002). Automatic hierarchical object decomposition for object recognition. In International Archives of Photogrammetry and Remote Sensing, volume XXXIV, part 5, pages 99-104.
  19. Zhang, J., Collins, R., and Liu, Y. (2004). Representation and matching of articulated shapes. In Computer Vision and Pattern Recognition, volume 2, pages 342- 349.
Download


Paper Citation


in Harvard Style

Hofhauser A., Steger C. and Navab N. (2008). HARMONIC DEFORMATION MODEL FOR EDGE BASED TEMPLATE MATCHING . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 75-82. DOI: 10.5220/0001071800750082


in Bibtex Style

@conference{visapp08,
author={Andreas Hofhauser and Carsten Steger and Nassir Navab},
title={HARMONIC DEFORMATION MODEL FOR EDGE BASED TEMPLATE MATCHING},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={75-82},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001071800750082},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - HARMONIC DEFORMATION MODEL FOR EDGE BASED TEMPLATE MATCHING
SN - 978-989-8111-21-0
AU - Hofhauser A.
AU - Steger C.
AU - Navab N.
PY - 2008
SP - 75
EP - 82
DO - 10.5220/0001071800750082