Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Discrete-continuous optimization for multi-target tracking

: Andriyenko, Anton; Schindler, Konrad; Roth, Stefan


IEEE Computer Society:
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 : Providence, Rhode Island, USA, 16 - 24 June 2012
New York, NY: IEEE, 2012
ISBN: 978-1-4673-1226-4 (Print)
ISBN: 978-1-4673-1228-8
ISBN: 978-1-4673-1227-1 (Online)
Conference on Computer Vision and Pattern Recognition (CVPR) <30, 2012, Providence/RI>
Conference Paper
Fraunhofer IGD ()
computer vision; people tracking; Markov random fields (MRF); optimization; Forschungsgruppe Visual Inference (VINF)

The problem of multi-target tracking is comprised of two distinct, but tightly coupled challenges: (i) the naturally discrete problem of data association, i.e. assigning image observations to the appropriate target; (ii) the naturally continuous problem of trajectory estimation, i.e. recovering the trajectories of all targets. To go beyond simple greedy solutions for data association, recent approaches often perform multi-target tracking using discrete optimization. This has the disadvantage that trajectories need to be pre-computed or represented discretely, thus limiting accuracy.
In this paper we instead formulate multi-target tracking as a discrete continuous optimization problem that handles each aspect in its natural domain and allows leveraging powerful methods for multi-model fitting. Data association is performed using discrete optimization with label costs, yielding near optimality. Trajectory estimation is posed as a continuous fitting problem with a simple closed-form solution, which is used in turn to update the label costs. We demonstrate the accuracy and robustness of our approach with state-of-the art performance on several standard datasets.