CONTINUOUS EDGE GRADIENT-BASED TEMPLATE MATCHING FOR ARTICULATED OBJECTS

Daniel Mohr, Gabriel Zachmann

Abstract

In this paper, we propose a novel edge gradient based template matching method for object detection. In contrast to other methods, ours does not perform any binarization or discretization during the online matching. This is facilitated by a new continuous edge gradient similarity measure. Its main components are a novel edge gradient operator, which is applied to query and template images, and the formulation as a convolution, which can be computed very efficiently in Fourier space. We compared our method to a state-of-the-art chamfer based matching method. The results demonstrate that our method is much more robust against weak edge response and yields much better confidence maps with fewer maxima that are also more significant. In addition, our method lends itself well to efficient implementation on GPUs: at a query image resolution of 320×256 and a template resolution of 80×80 we can generate about 330 confidence maps per second.

References

  1. Athitsos, V. and Sclaroff, S. (2001). 3d hand pose estimation by finding appearance-based matches in a large database of training views. In IEEE Workshop on Cues in Communication.
  2. Barrow, H. G., Tenenbaum, J. M., Bolles, R. C., and Wolf, H. C. (1977). Parametric correspondence and chamfer matching: Two new techniques for image matching. In International Joint Conference on Artificial Intelligence.
  3. Gavrila, D. M. and Philomin, V. (1999). Real-time object detection for smart vehicles. In IEEE International Conference on Computer Vision.
  4. Huttenlocher, D., Klanderman, G. A., and Rucklidge, W. J. (1993). Comparing images using the hausdorff distance. In IEEE Transactions on Pattern Analysis and Machine Intelligence.
  5. Mohr, D. and Zachmann, G. (2009). Continuous edge gradient-based template matching for articulated objects. In Technical Report.
  6. Nvidia (2008). Compute unified device architecture.
  7. Olson, C. F. and Huttenlocher, D. P. (1997). Automatic target recognition by matching oriented edge pixels. In IEEE Transactions on Image Processing.
  8. Shaknarovich, G., Viola, P., and Darrell, T. (2003). Fast pose estimation with parameter-sensitive hashing. In IEEE International Conference on Computer Vision.
  9. Stenger, B., Thayananthan, A., Torr, P. H. S., and Cipolla, R. (2006). Model-based hand tracking using a hierarchical bayesian filter. In IEEE Transactions on Pattern Analysis and Machine Intelligence.
  10. Sudderth, E. B., Mandel, M. I., Freeman, W. T., and Willsky, A. S. (2004). Visual hand tracking using nonparametric belief propagation. In IEEE CVPR Workshop on Generative Model Based Vision.
  11. Thayananthan, A., Navaratnam, R., Stenger, B., Torr, P., and Cipolla, R. (2006). Multivariate relevance vector machines for tracking. In European Conference on Computer Vision.
Download


Paper Citation


in Harvard Style

Mohr D. and Zachmann G. (2009). CONTINUOUS EDGE GRADIENT-BASED TEMPLATE MATCHING FOR ARTICULATED OBJECTS . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 519-524. DOI: 10.5220/0001800805190524


in Bibtex Style

@conference{visapp09,
author={Daniel Mohr and Gabriel Zachmann},
title={CONTINUOUS EDGE GRADIENT-BASED TEMPLATE MATCHING FOR ARTICULATED OBJECTS},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={519-524},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001800805190524},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)
TI - CONTINUOUS EDGE GRADIENT-BASED TEMPLATE MATCHING FOR ARTICULATED OBJECTS
SN - 978-989-8111-69-2
AU - Mohr D.
AU - Zachmann G.
PY - 2009
SP - 519
EP - 524
DO - 10.5220/0001800805190524