Abstract
This paper investigates the use of elliptic Fourier descriptors as a shape descriptor forencoding the silhouette of a person. Shape descriptors are here used for predicting the shape ofsilhouettes in missing frames within a sequence. This prediction scheme is applied to the caseof generating in-between images in a low frame rate videoconferencing system, where thereconstructed silhouette is used as a binary mask for reducing the computational time for theframe reconstruction.
Lingua originale | English |
---|---|
pagine (da-a) | 391-408 |
Numero di pagine | 18 |
Rivista | Journal of Visual Languages and Computing |
Volume | 15 |
Stato di pubblicazione | Published - 2004 |
All Science Journal Classification (ASJC) codes
- ???subjectarea.asjc.1200.1203???
- ???subjectarea.asjc.1700.1709???
- ???subjectarea.asjc.1700.1706???