Abstract
In particle filtering, dimensionality of the state space can be reduced by tracking control (or feature) points as independent objects, which are traditionally named as partitions. Two critical decisions have to be made in implementation of reduced state-space dimensionality. First is how to construct a dynamic (transition) model for partitions that are inherently dependent. Second critical decision is how to filter partition states such that a viable and likely object state is achieved. In this study, we present a correlation-based transition model and a proposal function that incorporate partition dependency in particle filtering in a computationally tractable manner. We test our algorithm on challenging examples of occlusion, clutter and drastic changes in relative speeds of partitions. Our successful results with as low as 10 particles per partition indicate that the proposed algorithm is both robust and efficient.
Similar content being viewed by others
References
Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Eng-T ASME 82(Series D), 35–45 (1960)
Isard, M., Blake, A.: Condensation—conditional density propagation for visual tracking. Int. J. Comput. Vis. 29(1), 5–28 (1998)
Pitt, M., Shephard, N.: Filtering via simulation: auxiliary particle filtering. J. Am. Stat. Assoc. 94, 590–599 (1999)
Blake, A., Curwen, R., Zisserman, A.: A framework for spatio-temporal control in the tracking of visual contours. Int. J. Comput. Vis. 11(2), 127–145 (1993)
MacCormick, J.: Probabilistic modeling and stochastic algorithms for visual localisation and tracking. Ph.D. Dissertation, University of Oxford (2000)
Hue, C., Le Cadre, J.-P., Perez, P.: Tracking multiple objects with particle filtering. Aerosp. Electron. Syst. IEEE Trans. 38(3), 791–812 (2002)
MacCormick, J., Blake, A.: A probabilistic exclusion principle for tracking multiple objects. Int. J. Comput. Vis. 39(1), 57–71 (2000)
MacCormick, J., Isard, M.: Partitioned sampling, articulated objects, and interface-quality hand tracking. In: Proceedings of the 6th European Conference on Computer Vision-Part II, ser. ECCV’ 00, pp. 3–19. Springer, London (2000)
Deutscher, J., Reid, I.: Articulated body motion capture by stochastic search. Int. J. Comput. Vis. 61(2), 185–205 (2005)
Wu, B., Nevatia, R.: Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors. Int. J. Comput. Vis. 75(2), 247–266 (2007)
Patras, I., Pantic, M.: Particle filtering with factorized likelihoods for tracking facial features. In: Automatic Face and Gesture Recognition, 2004. Proceedings. Sixth IEEE International Conference on, May 2004, pp. 97–102 (2004)
Dai, X., Hager, G.D.: Efficient particle filtering using RANSAC with application to 3d face tracking. Image Vis. Comput. 24, 581–592 (2006)
Valstar, M., Pantic, M.: Fully automatic facial action unit detection and temporal analysis. In: Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop, ser. CVPRW ’06, pp. 149–154. IEEE Computer Society, Washington (2006) (Online). doi:10.1109/CVPRW.2006.85
Pogalin, E., Redert, A., Patras, I., Hendriks, E.: Gaze tracking by using factorized likelihoods particle filtering and stereo vision. In: 3D Data Processing, Visualization, and Transmission, Third International Symposium on, June 2006, pp. 57–64 (2006)
Lepetit, V., Pilet, J., Fua, P.: Point matching as a classification problem for fast and robust object pose estimation. In: Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on, vol. 2, pp. II-244–II-250 (2004)
Oliver, N.M., Rosario, B., Pentland, A.P.: A Bayesian computer vision system for modeling human interactions. IEEE T. Pattern Anal. 22(8), 831–843 (2000)
Taycher, L., Fisher III, J.W., Darrell, T.: Combining object and feature dynamics in probabilistic tracking. Comput. Vis. Image Underst. 108(3), 243–260 (2007). doi:10.1016/j.cviu.2006.11.022
Triesch, J., Von Der Malsburg, C.: Democratic integration: self-organized integration of adaptive cues. Neural Comput. 13(9), 2049–2074 (2001)
Bréthes, L., Lerasle, F., Danés, P., Fontmarty, M.: Particle filtering strategies for data fusion dedicated to visual tracking from a mobile robot. Mach. Vis. Appl. 21(4), 427–448 (2010). doi:10.1007/s00138-008-0174-7
Erdem, E., Dubuisson, S., Bloch, I.: Fragments based tracking with adaptive cue integration. Comput. Vis. Image Underst. 116(7), 827–841 (2012). doi:10.1016/j.cviu.2012.03.005
McKenna, S.J., Nait-Charif, H.: Tracking human motion using auxiliary particle filters and iterated likelihood weighting. Image Vis. Comput. 25(6), 852–862 (2007). doi:10.1016/j.imavis.2006.06.003
Coşar, S., Çetin, M.: A graphical model based solution to the facial feature point tracking problem. Image Vis. Comput. 29(5), 335–350 (2011). doi:10.1016/j.imavis.2010.12.001
Zhang, L., van der Maaten, L.: Structure preserving object tracking. In: Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, ser. CVPR ’13, pp. 1838–1845. IEEE Computer Society, Washington, DC (2013) (Online). doi:10.1109/CVPR.2013.240
Pantic, M., Valstar, M.F., Rademaker, R., Maat, L.: Web-based database for facial expression analysis. In: Proceedings of IEEE Int’l Conf. Multimedia and Expo (ICME’05), Amsterdam, The Netherlands, pp. 317–321 (2005)
Fish species. http://fish-species.org.uk/. Accessed 17 Apr 2014
Filters, U.: Tracking football player movement from a single moving camera. In: Visual Media Production, 2006. CVMP 2006. 3rd European Conference on, pp. 29–37 (2006)
Hassan, W., Bangalore, N., Birch, P., Young, R.C.D., Chatwin, C.R.: An adaptive sample count particle filter. Comput. Vis. Image Underst. 116(12), 1208–1222 (2012)
Acknowledgments
This research is part of project “Expression Recognition based on Facial Anatomy”, grant number 109E061, supported by The Support Programme for Scientific and Technological Research Projects of The Scientific and Technological Research Council of Turkey (TÜBİTAK). In comparative evaluation of the tracking algorithms we utilized the SPOT tracking code that was made publicly available by researchers Lu Zhang and Laurens van der Maaten. A special thanks to Fish Species who generously provided the high definition aquarium videos used in our experiments (http://www.fish-species.org.uk).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Taner Eskil, M. Factored particle filtering with dependent and constrained partition dynamics for tracking deformable objects. Machine Vision and Applications 25, 1825–1840 (2014). https://doi.org/10.1007/s00138-014-0634-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-014-0634-1