Abstract
We present an object tracking framework that employs Dirichlet Process Mixture Models (DPMMs) in a multiple hypothesis tracker. DPMMs enable joint detection and tracking of an unknown and variable number of objects in a fully automatic fashion without any initial labeling. At each frame, we extract foreground superpixels and cluster them into objects by propagating clusters across consecutive frames. Since no constraint on the number of clusters is required, we can track multiple cluster hypotheses at the same time. By incorporating superpixels and an efficient pruning scheme, we keep the total number of hypotheses low and tractable. We refine object boundaries with Markov random fields and connectivity analysis of the tracked clusters. Finally, we group tracked hypotheses to combine possible parts of an object as one.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Reid, D.B.: An algorithm for tracking multiple targets. IEEE Transactions on Automatic Control 24, 843–854 (1979)
Fortmann, T., Bar-Shalom, Y., Scheffe, M.: Multi-target tracking using joint probabilistic data association, pp. 807–812 (1980)
Arulampalam, M.S., Maskell, S., Gordon, N.: A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Transactions on Signal Processing 50, 174–188 (2002)
Özkan, E., Özbek, I.Y., Demirekler, M.: Dynamic speech spectrum representation and tracking variable number of vocal tract resonance frequencies with time-varying dirichlet process mixture models. IEEE Transactions on Audio, Speech & Language Processing 17, 1518–1532 (2009)
Neiswanger, W., Wood, F.: Unsupervised Detection and Tracking of Arbitrary Objects with Dependent Dirichlet Process Mixtures. ArXiv e-prints (2012)
Antoniak, C.E.: Mixtures of Dirichlet Processes with Applications to Bayesian Nonparametric Problems. The Annals of Statistics 2, 1152–1174 (1974)
Neal, R.M.: Markov chain sampling methods for dirichlet process mixture models. Journal of Computational And Graphical Statistics 9, 249–265 (2000)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S.: SLIC Superpixels Compared to State-of-the-art Superpixel Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1 (2012)
Stauffer, C., Grimson, E.: Adaptive background mixture models for real-time tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999 (2002)
Sudderth, E.: Graphical Models for Visual Object Recognition and Tracking. PhD thesis, Massachusetts Institute of Technology (2006)
Casella, G., Robert, C.P.: Rao-blackwellisation of sampling schemes. Biometrika 83, 81–94 (1996)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 2001 (2001)
Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/
Komodakis, N., Tziritas, G.: Approximate labeling via graph cuts based on linear programming. IEEE Trans. Pattern Anal. Mach. Intell. 29, 1436–1453 (2007)
Komodakis, N., Tziritas, G., Paragios, N.: Performance vs computational efficiency for optimizing single and dynamic mrfs: Setting the state of the art with primal-dual strategies. Comput. Vis. Image Underst. 112, 14–29 (2008)
Bradski, G.: The OpenCV Library. Dr. Dobb’s Journal of Software Tools (2000)
Bernardini, F., Bajaj, C.L.: Sampling and reconstructing manifolds using alpha-shapes. In: Proc. 9th Canad. Conf. Comput. Geom. (1997)
CGAL: Computational Geometry Algorithms Library, http://www.cgal.org
PETS 2001: Second IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (2001), ftp://ftp.pets.rdg.ac.uk/pub/PETS2001/
PETS 2009: Eleventh IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (2009), ftp://ftp.pets.rdg.ac.uk/pub/PETS2009/
Kasturi, R., Goldgof, D., Soundararajan, P., Manohar, V., Garofolo, J., Bowers, R., Boonstra, M., Korzhova, V., Zhang, J.: Framework for performance evaluation of face, text, and vehicle detection and tracking in video: Data, metrics, and protocol. IEEE Trans. Pattern Anal. Mach. Intell. 31, 319–336 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Topkaya, I.S., Erdogan, H., Porikli, F. (2013). Detecting and Tracking Unknown Number of Objects with Dirichlet Process Mixture Models and Markov Random Fields. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2013. Lecture Notes in Computer Science, vol 8034. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41939-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-41939-3_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41938-6
Online ISBN: 978-3-642-41939-3
eBook Packages: Computer ScienceComputer Science (R0)