License
When quoting this document, please refer to the following
URN: urn:nbn:de:0030-drops-16173
URL: http://drops.dagstuhl.de/opus/volltexte/2008/1617/
Go to the corresponding Portal


Ess, Andreas ; Schindler, Konrad ; Leibe, Bastian ; van Gool, Luc

Robust Multi-Person Tracking from Moving Platforms

pdf-format:
Document 1.pdf (547 KB)


Abstract

In this paper, we address the problem of multi-person tracking in busy pedestrian zones, using a stereo rig mounted on a mobile platform. The complexity of the problem calls for an integrated solution, which extracts as much visual information as possible and combines it through cognitive feedback. We propose such an approach, which jointly estimates camera position, stereo depth, object detection, and tracking. We model the interplay between these components using a graphical model. Since the model has to incorporate object-object interactions, and temporal links to past frames, direct inference is intractable. We therefore propose a two-stage procedure: for each frame we first solve a simplified version of the model (disregarding interactions and temporal continuity) to estimate the scene geometry and an overcomplete set of object detections. Conditioned on these results, we then address object interactions, tracking, and prediction in a second step. The approach is experimentally evaluated on several long and difficult video sequences from busy inner-city locations. Our results show that the proposed integration makes it possible to deliver stable tracking performance in scenes of realistic complexity.

BibTeX - Entry

@InProceedings{ess_et_al:DSP:2008:1617,
  author =	{Andreas Ess and Konrad Schindler and Bastian Leibe and Luc van Gool},
  title =	{Robust Multi-Person Tracking from Moving Platforms},
  booktitle =	{Logic and Probability for Scene Interpretation },
  year =	{2008},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M{\"o}ller and Bernd Neumann},
  number =	{08091},
  series =	{Dagstuhl Seminar Proceedings},
  ISSN =	{1862-4405},
  publisher =	{Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2008/1617},
  annote =	{Keywords: Pedestrian detection, tracking, Mobile vision}
}

Keywords: Pedestrian detection, tracking, Mobile vision
Seminar: 08091 - Logic and Probability for Scene Interpretation
Issue Date: 2008
Date of publication: 23.10.2008


DROPS-Home | Fulltext Search | Imprint Published by LZI