UWA Logo
  Faculty Home | School Home | Internal Page | Awesome Animations   
           
Home
About the School
Contact and People
Future Undergraduate Students
Prospective Postgraduates
Current Students
Current Postgraduates
Research
IT News
Awards
Industry Links and Prizes
School and IT Information
Other
Internal Information

Research Seminar - April 17, 2003

Automated Location Matching in Movies

Andrew Zisserman
Department of Engineering Science
University of Oxford
12pm Thursday 17th April, 2003
Computer Science & Software Engineering
Seminar Room 1.24

Abstract:

We describe progress in matching shots which are images of the same 3D location in a film. The problem is hard because the camera viewpoint may change substantially between shots, with consequent changes in the imaged appearance of the scene due to foreshortening, scale changes, partial occlusion and lighting changes.

We describe how "wide baseline" matching methods can be developed to solve this problem. The wide baseline method represents each frame by a set of viewpoint invariant local features. The local spatial support of the features means that segmentation of the frame (e.g. into foreground/background) is not required, and partial occlusion is tolerated.

Results of matching shots for a number of different scene types are illustrated on an entire commercial film.

Top of Page