Title
Object based refinement of motion vector fields applying probabilistic homogenization rules
Abstract
This paper presents a new image analysis method, combining motion estimation and image segmentation. Whereas none of these methods, used on its own, delivers error free meta-information, an appropriate combination leads to an orthogonalization of these errors. This method is applied to improve the quality of motion vector fields.
Year
DOI
Venue
2002
10.1109/TCE.2002.1037063
Consumer Electronics, IEEE Transactions
Keywords
Field
DocType
video signal processing,probabilistic homogenization rules,error free meta-information,image quality,error orthogonalization,image segmentation,motion estimation,image analysis,field rate upconversion,object detection,video signal,motion vector fields,probability,object based refinement
Computer vision,Object detection,Pattern recognition,Computer science,Homogenization (chemistry),Image quality,Image segmentation,Artificial intelligence,Motion estimation,Probabilistic logic,Orthogonalization,Motion vector
Journal
Volume
Issue
ISSN
48
3
0098-3063
Citations 
PageRank 
References 
9
0.98
6
Authors
4
Name
Order
Citations
PageRank
H. Blume1897.99
Herczeg, G.290.98
Erdler, O.390.98
Tobias G. Noll419937.51