Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | IMDSP-P11.4 |
| Session: | Video Analysis |
| Time: | Friday, May 21, 09:30 - 11:30 |
| Presentation: |
Poster |
| Topic: |
Image and Multidimensional Signal Processing: Image and Video Analysis |
| Title: |
APPEARANCE-BASED TRACKING AND RECOGNITION USING THE 3D TRILINEAR TENSOR |
| Authors: |
Jie Shao; University of Maryland, College Park | | |
| | Shaohua Zhou; University of Maryland, College Park | | |
| | Rama Chellappa; University of Maryland, College Park | | |
| Abstract: |
The paper presents an appearance-based adaptive algorithm forsimultaneous tracking and recognition by generalizing thetransformation model to 3D perspective transformation. A trilineartensor operator is used to represent the 3D geometrical structure.The tensor is estimated by predicting the corresponding pointsusing the existing affine-transformation based algorithm. Theestimated tensor is used to synthesize novel views to update theappearance templates. Some experimental results using airbornevideo are presented. |
| |
| Back | |