Serviceeinschränkungen vom 12.-22.02.2026 - weitere Infos auf der UB-Homepage

Treffer: Semi-automatic modifications of video object trajectories for video compositing applications

Title:
Semi-automatic modifications of video object trajectories for video compositing applications
Source:
Signal processing. 85(10):1970-1983
Publisher Information:
Amsterdam: Elsevier Science, 2005.
Publication Year:
2005
Physical Description:
print, 18 ref
Original Material:
INIST-CNRS
Document Type:
Fachzeitschrift Article
File Description:
text
Language:
English
Author Affiliations:
IRISA/INRIA, Campus de Beaulieu, 35042 Rennes, France
ISSN:
0165-1684
Rights:
Copyright 2005 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Telecommunications and information theory
Accession Number:
edscal.17090584
Database:
PASCAL Archive

Weitere Informationen

This paper proposes a new approach allowing efficient and semi-automatic object-based manipulation for video editing or post-production applications, such as the modification of the trajectories of video objects in a natural scene. For that purpose, an image is seen as a superposition of video object planes (VOP) on an original image or a mosaic view of a fixed background. The method is based on the definition of an editing scenario which contains all the information required to create the edited sequence. A warping model is used to represent the location and the modification of the video object in the 2-D scene. Such an application is by nature semi-automatic since the operator has to specify the modifications that he wants to perform on the original sequence. The proposed method has been designed in order to reduce as much as possible the human workload by using the notion of key VOP and by calibrating in depth the fixed background area. Experimental results show that a high level of realism can be obtained on edited images in which the original trajectories of non-rigid video objects have been strongly modified.