Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

An analytical formulation of global occlusion reasoning for multi-target tracking

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


Institute of Electrical and Electronics Engineers -IEEE-:
IEEE International Conference on Computer Vision, ICCV Workshops 2011 : 6-13 November 2011, Barcelona, Spain
Piscataway/NJ: IEEE, 2011
ISBN: 978-1-4673-0062-9 (online)
ISBN: 978-1-4673-0063-6
International Conference on Computer Vision (ICCV) <13, 2011, Barcelona>
International Workshop on Visual Surveillance (VS) <11, 2011, Barcelona>
Fraunhofer IGD ()
computer vision; people tracking; tracking; Occlusion model; computer vision based tracking; Forschungsgruppe Visual Inference (VINF)

We present a principled model for occlusion reasoning in complex scenarios with frequent inter-object occlusions, and its application to multi-target tracking. To compute the putative overlap between pairs of targets, we represent each target with a Gaussian. Conveniently, this leads to an analytical form for the relative overlap - another Gaussian - which is combined with a sigmoidal term for modeling depth relations. Our global occlusion model bears several advantages: Global target visibility can be computed efficiently in closed-form, and varying degrees of partial occlusion can be naturally accounted for. Moreover, the dependence of the occlusion on the target locations - i.e. the gradient of the overlap - can also be computed in closedform, which makes it possible to efficiently include the proposed occlusion model in a continuous energy minimization framework. Experimental results on seven datasets confirm that the proposed formulation consistently reduces missed targets and lost trajectories, especially in challenging scenarios with crowds and severe inter-object occlusions.