Dataset 1

TRICTRAC Test Case Scenarios

Introduction

For the TRICTRAC project a number of video clips were rendered. For the first rendering campaign, 3 scenarios were tested with several cameras.

Scenarios

There are 3 scenarios, we give the description with some key frames.

View Scenario 1

View Scenario 2

View Scenario 3

Camera

For the dataset, We used 5 different virtual cameras. The camera 9 is used with two different fields of view.

Dataset

This is the Dataset provided. We suggest to use the Avi files only for quick prototyping, but use the higher quality sequences in Jpegs for real testing.

Ground truth

The ground truth is in XML format and decribes the PTZ parameters of cameras, the positions of players both in the image and in the 3D world space of the field.

Licence

All data is publicly available and downloadable. If you publish results using the data, please acknowledge the data as coming from the TRICTRAC project, found at URL: http://www.multitel.be/trictrac.
THE DATASET IS PROVIDED WITHOUT WARRANTY OF ANY KIND.

Links

• http://homepages.inf.ed.ac.uk/rbf/CAVIAR/: CAVIAR, Context Aware Vision using Image-based Active Recognition Project.
• www.visualsurveillance.org: For information on the 4th & 5th  IEEE International Workshops on Performance Evaluation of Tracking and Surveillance.
• http://www.multitel.be/~va/candela: Material from CANDELA project for performance evaluation of content analysis.
• www.etiseo.net: Video Understanding Evaluation ETISEO Project.
• www.ogre3d.org: Object-Oriented Graphics Rendering Engine (we used it to render the 3D scenes)

Comments

Please give all your comments, so we will increase the quality of the material for the TRICTRAC DATASET-2