REPAIRING PEOPLE TRAJECTORIES BASED ON POINT CLUSTERING

Chau Duc Phu, François Brémond, Etienne Corvée, Monique Thonnat

2009

Abstract

This paper presents a method for improving any object tracking algorithm based on machine learning. During the training phase, important trajectory features are extracted which are then used to calculate a confidence value of trajectory. The positions at which objects are usually lost and found are clustered in order to construct the set of ‘lost zones’ and ‘found zones’ in the scene. Using these zones, we construct a triplet set of zones i.e. 3 zones: In/Out zone (zone where an object can enter or exit the scene), ‘lost zone’ and ‘found zone’. Thanks to these triplets, during the testing phase, we can repair the erroneous trajectories according to which triplet they are most likely to belong to. The advantage of our approach over the existing state of the art approaches is that (i) this method does not depend on a predefined contextual scene, (ii) we exploit the semantic of the scene and (iii) we have proposed a method to filter out noisy trajectories based on their confidence value.

References

  1. A. Almeida, J. Almeida, and R. Araujo, Real-time tracking of multiple moving objects using particle filters and probabilistic data association, Automatika, vol. 46, no. 1-2, pp. 39-48, 2005.
  2. A. Avanzi, Francois Bremond, Christophe Tornieri and Monique Thonnat, Design and Assessment of an Intelligent Activity Monitoring Platform, in EURASIP Journal on Applied Signal Processing, special issue in "Advances in Intelligent Vision Systems: Methods and Applications", 2005:14, pp.2359-2374.
  3. E. Brookner, John Wiley & Sons, Tracking and Kalman Filtering Made Easy, 1998.
  4. Fernyhough, J H, Cohn, A G & Hogg, D C Generation of semantic regions from image sequences in: Buxton, B & Cipolla, R (editors) ECCV'96, pp.475-478. Springer-Verlag. 1996.
  5. D. Makris, T. Ellis, Learning semantic scene models from observing activity in visual surveillance, IEEE Transactions on Systems, Man and Cybernetics, Part B 35 (3) (2005) 397-408.
  6. S. Maskell, N. Gordon, M. Rollason and D. Salmond, Efficient Multitarget Tracking using Particle Filters, Journal in Image and Vision Computing, 21(10): 931- 939, September 2003.
  7. Raquel R. Pinho, João Manuel R. S. Tavares, Miguel V. Correia, An Efficient and Robust Tracking System using Kalman Filter, VIPSI-2006 VENICE, 2006.
  8. Raquel R. Pinho1, João Manuel R. S. Tavares and Miguel V. Correia, A Movement Tracking Management Model with Kalman Filtering, Global Optimization Techniques and Mahalanobis Distance, Lecture Series on Computer and Computational Sciences Volume 1, 2005, pp. 1-3.
Download


Paper Citation


in Harvard Style

Duc Phu C., Brémond F., Corvée E. and Thonnat M. (2009). REPAIRING PEOPLE TRAJECTORIES BASED ON POINT CLUSTERING . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 449-456. DOI: 10.5220/0001778904490456


in Bibtex Style

@conference{visapp09,
author={Chau Duc Phu and François Brémond and Etienne Corvée and Monique Thonnat},
title={REPAIRING PEOPLE TRAJECTORIES BASED ON POINT CLUSTERING},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={449-456},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001778904490456},
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 1: VISAPP, (VISIGRAPP 2009)
TI - REPAIRING PEOPLE TRAJECTORIES BASED ON POINT CLUSTERING
SN - 978-989-8111-69-2
AU - Duc Phu C.
AU - Brémond F.
AU - Corvée E.
AU - Thonnat M.
PY - 2009
SP - 449
EP - 456
DO - 10.5220/0001778904490456