Towards Embedded Robot Vision for Multi-scale Object Recognition - Repeatability of Interest Points Detected in Half-octave Binomial Pyramids

Peter Andreas Entschev, Hugo Vieira Neto

Abstract

The construction of multi-scale image pyramids is used in state-of-the-art methods that perform robust object recognition, such as SIFT and SURF. However, building such image pyramids is computationally expensive, especially when implementations in embedded systems with limited computing resources are considered. Therefore, the use of alternative less expensive approaches are necessary if near real-time operation is desired. Previous work has reported that using binomial filters to construct half-octave multi-scale pyramids consumes only 1=4 of the processing time of the Gaussian pyramid originally used in the SIFT framework. Here we investigate how interest points detected using the binomial approach behave when compared to the Gaussian approach, focusing on repeatability. Experimental results show that in average up to 86% of interest points detected with the original SIFT pyramid building scheme are also detected when using the binomial method, despite of large gains in processing time. When rotation of image features is considered, experimental results demonstrate that slightly superior repeatability of interest points is achieved using the binomial pyramid.

References

  1. Bay, H., Ess, A., Tuytelaars, T., and Van Gool, L. (2008). Speeded-up robust features (surf). Computer Vision and Image Understanding, 110(3):346-359.
  2. Bradski, G. and Kaehler, A. (2008). Learning OpenCV: Computer Vision with the OpenCV library. O'Reilly Media.
  3. Brown, M. and Lowe, D. G. (2002). Invariant features from interest point groups. In Proceedings of the 13th British Machine Vision Conference.
  4. Burt, P. and Adelson, E. (1983). The laplacian pyramid as a compact image code. IEEE Transactions on Communications, 31(4):532-540.
  5. Coley, G. (2010). Beagleboard-xm system reference manual, revision A2. Beagleboard.org.
  6. Crowley, J. L. and Riff, O. (2003). Fast computation of scale normalised gaussian receptive fields. In Scale Space Methods in Computer Vision, pages 584-598. Springer.
  7. Crowley, J. L., Riff, O., and Piater, J. (2002). Fast computation of characteristic scale using a half octave pyramid. In Proceedings of the International Workshop on Cognitive Vision.
  8. Crowley, J. L. and Stern, R. M. (1984). Fast computation of the difference of low-pass transform. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6(2):212-222.
  9. Entschev, P. A. and Vieira Neto, H. (2013). Efficient construction of SIFT multi-scale image pyramids for embedded robot vision. In Proceedings of TAROS 2013: Towards Autonomous Robotic Systems.
  10. Halfacree, G. and Upton, E. (2012). Raspberry Pi User Guide. Wiley.
  11. Lowe, D. G. (1999). Object recognition from local scaleinvariant features. In Proceedings of the 7th IEEE international Conference on Computer Vision, volume 2, pages 1150-1157. IEEE.
  12. Lowe, D. G. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision, 60(2):91-110.
  13. Lowe, D. G. (2005). Demo software: SIFT keypoint detector. University of British Columbia. http://www. cs.ubc.ca/ lowe/keypoints/.
  14. Mikolajczyk, K. and Schmid, C. (2004). Scale & affine invariant interest point detectors. International Journal of Computer Vision, 60(1):63-86.
  15. Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume 1, pages 511-518.
  16. Visual Geometry Group (2004). Affine covariant regions dataset. University of Oxford. http://www.robots.ox. ac.uk/ vgg/data/data-aff.html.
Download


Paper Citation


in Harvard Style

Andreas Entschev P. and Vieira Neto H. (2014). Towards Embedded Robot Vision for Multi-scale Object Recognition - Repeatability of Interest Points Detected in Half-octave Binomial Pyramids . In Proceedings of the 4th International Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PECCS, ISBN 978-989-758-000-0, pages 97-103. DOI: 10.5220/0004700200970103


in Bibtex Style

@conference{peccs14,
author={Peter Andreas Entschev and Hugo Vieira Neto},
title={Towards Embedded Robot Vision for Multi-scale Object Recognition - Repeatability of Interest Points Detected in Half-octave Binomial Pyramids},
booktitle={Proceedings of the 4th International Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PECCS,},
year={2014},
pages={97-103},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004700200970103},
isbn={978-989-758-000-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PECCS,
TI - Towards Embedded Robot Vision for Multi-scale Object Recognition - Repeatability of Interest Points Detected in Half-octave Binomial Pyramids
SN - 978-989-758-000-0
AU - Andreas Entschev P.
AU - Vieira Neto H.
PY - 2014
SP - 97
EP - 103
DO - 10.5220/0004700200970103