REFA3D: ROBUST SPATIO-TEMPORAL ANALYSIS OF VIDEO SEQUENCES

Manuel Grand-Brochier, Christophe Tilmant, Michel Dhome

Abstract

This article proposes a generalization of our approach REFA (Grand-brochier et al., 2011) to spatio-temporal domain. Our new method REFA3D, is based mainly on hes-STIP detector and E-HOG3D. SIFT3D and HOG/HOF are the two must used methods for space-time analysis and give good results. So their studies allow us to understand their construction and to extract some components to improve our approach. The mask of analysis used by REFA is modified and therefore relies on the use of ellipsoids. The validation tests are based on video clips from synthetic transformations as well as real sequences from a simulator or an onboard camera. Our system (detection, description and matching) must be as invariant as possible for the image transformation (rotations, scales, time-scaling). We also study the performance obtained for registration of subsequence, a process often used for the location, for example. All the parameters (analysis shape, thresholds) and changes to the space-time generalization will be detailed in this article.

References

  1. Bay, H., Tuylelaars, T., and Gool, L. V. (2006). Surf : Speeded up robust features. European Conference on Computer Vision, pages 404-417.
  2. Delmas, P. (2011). Gnration active des dplacements d'un vhicule agricole dans son environnement. PhD thesis, University Blaise Pascal - Clermont II.
  3. Grand-brochier, M., Tilmant, C., and Dhome, M. (2011). Method of extracting interest points based on multiscale detector and local e-hog descriptor. International Conference on Computer Vision Theory and Applications.
  4. Klaser, A., Marszalek, M., and Schmid, C. (2008). A spatiotemporal descriptor based on 3d-gradients. British Machine Vision Conference, pages 995-1004.
  5. Laptev, I., Caputo, B., Schuldt, C., and Lindeberg, T. (2007). Local velocity-adapted motion events for spatio-temporal recognition. Computer Vision and Image Understanding, 108(3):207-229.
  6. Laptev, I. and Lindeberg, T. (2003). Space-time interest points. IEEE International Conference on Computer Vision, 1:432-439.
  7. Laptev, I. and Lindeberg, T. (2006). Local descriptors for spatio-temporal recognition. Computer and Information Science, 3667:91-103.
  8. Lowe, D. (1999). Object recognition from local scaleinvariant features. IEEE International Conference on Computer Vision, pages 1150-1157.
  9. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision, 60(2):91-110.
  10. Malartre, F. (2011). Perception intelligente pour la navigation rapide de robots mobiles en environnement naturel. PhD thesis, University Blaise Pascal - Clermont II.
  11. Scovanner, P., Ali, S., and Shah, M. (2007). A 3- dimensional sift descriptor and its application to action recognition. ACM Multimedia.
  12. Wang, H., Ullah, M., Klaser, A., Laptev, I., and Schmid, C. (2009). Evaluation of local spatio-temporal features for action recognition. British Machine Vision Conference.
  13. Willems, G., Tuytelaars, T., and Gool, L. V. (2008). An efficient dense and scale-invariant spatio-temporal interest point detector. European Conference on Computer Vision, 5303(2):650-663.
Download


Paper Citation


in Harvard Style

Grand-Brochier M., Tilmant C. and Dhome M. (2012). REFA3D: ROBUST SPATIO-TEMPORAL ANALYSIS OF VIDEO SEQUENCES . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 352-357. DOI: 10.5220/0003857203520357


in Bibtex Style

@conference{visapp12,
author={Manuel Grand-Brochier and Christophe Tilmant and Michel Dhome},
title={REFA3D: ROBUST SPATIO-TEMPORAL ANALYSIS OF VIDEO SEQUENCES},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={352-357},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003857203520357},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - REFA3D: ROBUST SPATIO-TEMPORAL ANALYSIS OF VIDEO SEQUENCES
SN - 978-989-8565-03-7
AU - Grand-Brochier M.
AU - Tilmant C.
AU - Dhome M.
PY - 2012
SP - 352
EP - 357
DO - 10.5220/0003857203520357