Segmentation of image sequences for object oriented coding

Publikationstyp
Conference Paper
Date Issued
1996
Sprache
English
Author(s)
Siggelkow, Sven  
Grigat, Rolf-Rainer  
Ibenthal, Achim  
Institut
Bildverarbeitungssysteme E-2  
TORE-URI
http://hdl.handle.net/11420/10287
Volume
2
Start Page
477
End Page
480
Citation
Proceedings, International Conference on Image Processing 2: 477-480 (1996-12)
Contribution to Conference
3rd IEEE International Conference on Image Processing, (ICIP 1996)  
Publisher DOI
10.1109/ICIP.1996.560892
Scopus ID
2-s2.0-0030384865
Publisher
IEEE
This paper presents an algorithm for segmentation of image sequences where especially aspects for object oriented coding are taken into account. A fundamental requirement of such applications is the temporal stability of the segmentation. This is improved in this article compared to other existing approaches by including motion estimation into the segmentation process. Additionally a hierarchical approach enables an efficient predictive coding on one hand and a semantic data access on the other hand. As a direct result from using full colour information for the segmentation process, coding of the chrominance information can be done with extremely high compression ratios. Thus there is nearly no extra coding effort for colour images compared to greyscale images.
DDC Class
004: Informatik