Séminaire Vision artificielle / Équipe Willow
Object and Scene Recognition in Large Datasets David Lowe (University of British Columbia, Canada) 16 novembre 2005 |
Many real-world applications of computer vision require recognizing small objects within large datasets containing thousands of images. This talk will describe some new algorithms for efficient indexing within large datasets, including randomized tree algorithms for fast nearest-neighbour matching and probabilistic methods that determine the minimal number of matches needed for reliable object detection. Some applications of these methods will be described for panorama recognition, location recognition for augmented reality, and a system that can identify any product in a supermarket from a partial image.
Écouter | ||
|
||
- Visualiser - Télécharger |
||
|
||
Télécharger | ||
|
![]() | David Lowe (University of British Columbia, Canada) David Lowe (University of British Columbia, Canada) |