Detecting and tracking unknown number of objects with Dirichlet process mixture models and Markov random fields
Topkaya, İbrahim Saygın and Erdoğan, Hakan and Porikli, Fatih (2013) Detecting and tracking unknown number of objects with Dirichlet process mixture models and Markov random fields. In: Bebis, George and Boyle, Richard and Parvin, Bahram and Koracin, Darko and Li, Baoxin and Porikli, Fatih and Zordan, Victor and Klosowski, James and Coquillart, Sabine and Luo, Xun and Chen, Min and Gotz, David, (eds.) Advances in Visual Computing: 9th International Symposium, ISVC 2013, Rethymnon, Crete, Greece, July 29-31, 2013. Proceedings, Part II. Lecture Notes in Computer Science, 8034. Springer, Berlin, pp. 178-188. ISBN 978-3-642-41938-6 (Print) 978-3-642-41939-3 (Online)
Full text not available from this repository.
Official URL: http://dx.doi.org/10.1007/978-3-642-41939-3_18
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.
Repository Staff Only: item control page