PETS '04 Preliminary Programme

9:00 - 9:30

Opening

• Welcome and Introduction to PETS ECCV'04, James L. Crowley
• PETS04 Surveillance Ground Truth Data Set, Robert B. Fisher

9:30 - 10:30Session 1 Metrics

• New Performance Evaluation Metrics for Object Detection Agorithms, Jacinto Nascimento and Jorge S. Marques
• Trajectory Distance Metric using Hidden Markov Model based Representation, Fatih Porikli

10:30 - 11:00

Coffee Break

11:00 - 12:30

Session 2 Automatic Regulation

• Robust Visual Tracking from Dynamic Control of Processing, Alban Caporossi, Daniela Hall, Patrick Reignier and James L.Crowley
• Automatic Tracking and Labeling of Human Activities in a video sequence, Fengjun Lv, Jinman Kang, Ram Nevatia, Isaac Cohen and Gerard Medioni
• Joint Appearance and Trajectory based Data Association for Multi-object Tracking, Arvind Lakshmikumar and Michael Burl

12:30 - 14:00

Lunch Break

14:00 - 15:30

Session 3 Semantics

• Is it Interesting? Comparing human and machine judgements on the PETS dataset, Hannah Dee and David Hogg
• Ontology-guided Training of Bayesian Networks for High Level Analysis in Visual Surveillance, Christopher Town
• On-line Tracking Groups of Pedestrians with Bayesian Networks, Pedro M. Jorge, Jorge S. Marques and Arnaldo J. Abrantes

15:30 - 16:00

Coffee Break

16:00 - 17:30

Session 4 Tracking Groups

• A Probabilistic model for an EM-like Object Tracking Algorithm using color histograms, Z. Zivkovic and Ben Krose
• Tracking Pedestrians in a Multiple Camera System with Trajectory Prediction and Occlusion Modeling, Jorge P. Batista
• Discussion: tracking algorithms and performance metrics