Paper Info
Title
An appearance based approach for video object extraction and representation
Abstract
We describe a novel appearance based scheme for extraction and representation of video objects. The tracking algorithm used for video object extraction is based upon a new eigen-space update scheme. We propose a scheme for organisation of video objects in an appearance based hierarchy. The appearance based hierarchy is constructed using a new SVD based eigen-space merging algorithm. The hierarchy enables approximate query resolution. Experiments performed on a large number of video sequences have yielded promising results.
Year
DOI
Venue
2002
10.1109/ICPR.2002.1048358
ICPR (2)
Keywords
Field
DocType
experiments,video object extraction,video sequences,tracking algorithm,svd,eigen-space update scheme,appearance based hierarchy,merging,appearance based approach,feature extraction,eigen-space merging algorithm,image sequences,object recognition,approximate query resolution,video object representation,video databases,eigenvalues and eigenfunctions,singular value decomposition,robustness,tracking,histograms,matrix decomposition,data mining
Computer vision,Histogram,Singular value decomposition,Pattern recognition,Computer science,Matrix decomposition,Robustness (computer science),Feature extraction,Video tracking,Artificial intelligence,Hierarchy,Cognitive neuroscience of visual object recognition
Conference
Volume
ISSN
Citations 
2
1051-4651
2
PageRank 
References 
Authors
0.43
7
4
Name
Order
Citations
PageRank
Gaurav Garg123220.61
Pramod Kumar2102.47
Santanu Chaudhury3897127.92
Ragini Chowdhury420.43