Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | IMDSP-L1.5 |
| Session: | Image and Video Analysis |
| Time: | Wednesday, May 19, 14:20 - 14:40 |
| Presentation: |
Lecture |
| Topic: |
Image and Multidimensional Signal Processing: Image and Video Analysis |
| Title: |
CONTOUR-BASED OBJECT TRACKING WITH GRADIENT-BASED CONTOUR ATTRACTION FIELD |
| Authors: |
Petr Dokládal; Paris School of Mines | | |
| | Raffi Enficiaud; Paris School of Mines | | |
| | Eva Dejnožková; Paris School of Mines | | |
| Abstract: |
The object tracking is a problem which is very often addressed by various approaches as the background subtraction, visual constancy or geometric flow, to cite only a few.The contribution of this paper is twofold: First, it proposes an enhanced feature-weighted gradient, enhancing the contours of the object characterized by this feature, and attenuating the gradient amplitude wherever the feature is not found.The second, and main contribution, is a new integrator for active-contours based tracking. It uses the gradient alongside the object contours and generates a bidirectional attraction field.The combination of the contour tracking and the weighted gradient is illustrated on the driver's-face tracking problem, where the illumination conditions (brightness, colour) change as the vehicle passes through different environments. |
| |
| Back | |