FIRST CALL FOR PARTICIPATION
                        ============================    


                    First IEEE International Workshop on

            Performance Evaluation of Tracking and Surveillance

                                 (PETS2000)

                               March 31st 2000

                       held in conjunction with FG'2000

          In Cooperation with IEEE Computer Society and the PAMI TC


Purpose
-----------------------------------------------------------------------

In recent years there has been considerable interest in the visual
surveillance of wide area scenes.
The recent, rapid increase in the number of CCTV cameras has
expedited the demand for automatic methods of processing their
output.

Successful tracking is the key to the automatic interpretation (e.g.
natural language descriptions) of scenes which, in turn, is of
considerable practical importance to surveillance applications, for
example, automated incident detection, the monitoring of major road
networks, shopping centres and shops, autonomous intelligent control
for vehicles etc.

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. This workshop aims to address this issue.
The workshop consists of a number of invited presentations from
leading researchers working in the area of visual surveillance, and a
panel discussion. The workshop is unique in that all participants are
testing algorithms on the same dataset - an image sequence of a
carpark environment containing both moving people and vehicles. The
dataset will be made available to participants of the workshop. The
aims of the workshop are several-fold:

   * to bring together researchers interested in the area of visual
     surveillance
   * to apply different algorithms to the same dataset(s)
   * to evaluate the differences between different models and
     algorithms
   * to discuss which criteria should be used for objective
     evaluation
   * to discuss how to document the performance (including accuracy)
     of visual surveillance algorithms
   * to discuss the development of a methodology for testing
     algorithms
   * to discuss the ongoing development of a testbed and guidelines
     for performing empirical   comparative tests.

Who should attend?  Anyone interested in visual surveilance and/or
performance evaluation/characterisation of vision algorithms.


Further Information
-----------------------------------------------------------------------

For further information please visit the main FG'2000 website at
http://www-prima.imag.fr/FG2000