One-day workshop organised in association with ICCV 2007, sponsored by the EPSRC project REASON (Robust Methods for Monitoring and Understanding People in Public Spaces). The datasets for the workshop were made possible by the support and collaboration of the British Airports Authority (BAA) Glasgow.
The electronic proceedings for this workshop can be downloaded here (PDF, 30Mb).
The datasets for PETS 2007 consider both volume crime (theft), and a threat scenario (unattended luggage.) Click on the link to the left to view the benchmark data.
*** The final programme for the workshop is available here ***
James Ferryman, University of Reading, UK
James L. Crowley, INP Grenoble, France
Justus Becker, TNO, Netherlands
Terry Boult, University of Colorado, USA
Giovanni Garibotto, ELSAG, Italy
David Cher, Silogic, France
Xavier Desurmont, Multitel ASBL, Belgium
Pierre-Alain Moellic, CEA, France
Sergio Velastin, Kingston University, UK
Arthur Pece, University of Copenhagen, Denmark
Justus Piater, University of Liege, Belgium
Fatih Porikli, MERL Technology Lab, USA
Carlo Regazzoni, University of Genova, Italy
Stan Sclaroff, Boston University, USA
Andrew Senior, IBM T.J.Watson Research Center, USA
Tieniu Tan, National Lab of Pattern Recognition, China
Monique Thonnat, INRIA Sophia-Antipolis, France
Visual surveillance is a major research area in computer vision. The recent rapid increase in the number of surveillance cameras has led to a strong demand for automatic methods of processing their outputs. The scientific challenge is to devise and implement automatic systems for obtaining detailed information about the activities and behaviours of people and vehicles observed by a single camera or by a network of cameras.
Visual Surveillance is a key technology in the following areas:
The growth in the development of the field has not been met with complementary systematic performance evaluation of developed techniques. It is especially difficult to make comparisons between algorithms if they have been tested on different datasets under widely varying conditions.
A one day workshop is being held in Rio de Janeiro in conjunction with ICCV 2007. The workshop continues the theme of the highly successful PETS workshops. This workshop aims to bring together researchers interested in performance evaluation of visual tracking and surveillance algorithms. The workshop is also unique in that all participants are evaluating algorithms on the same datasets. Further to this, the workshop is an opportunity to present and discuss methodologies and criteria for objective evaluation of visual surveillance algorithms.
For PETS 2007, the theme is multi-sensor event recognition in crowded public areas. A volume crime (theft), and a security threat (unattended luggage), are included.
Submissions are solicited which:
OR
The datasets will be made available to participants of the workshop session. The focus of the datasets is on the following types of event: i) loitering, ii) attended luggage removal ("theft"), and iii) left-luggage scenarios, of increasing complexity, captured using multiple sensors, within an airport terminal building setting.
Dr. James Ferryman,
Dr. Computational Vision Group,
School of Systems Engineering,
P.O. Box 225, Whiteknights,
Reading, UK, RG6 6AY. (map)
Tel: +44 118 378 6697, Fax: +44 118 975 1822.
Email: enquiries@pets2007.net