Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/84196
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: An analytical formulation of global occlusion reasoning for multi-target tracking
Author: Milan, A.
Roth, S.
Schindler, K.
Citation: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops): pp. 1839-1846
Publisher: IEEE
Publisher Place: USA
Issue Date: 2011
ISBN: 9781467300629
Conference Name: IEEE International Conference on Computer Vision Workshops (2011 : Barcelona, Spain)
Statement of
Responsibility: 
Anton Andriyenko, Stefan Roth, Konrad Schindler
Abstract: 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 closed-form, 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.
Rights: ©2011 IEEE
DOI: 10.1109/ICCVW.2011.6130472
Published version: http://dx.doi.org/10.1109/iccvw.2011.6130472
Appears in Collections:Aurora harvest
Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_84196.pdf
  Restricted Access
Restricted Access2.59 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.