Paper Info
Title
Utilization of the recursive shortest spanning tree algorithm for video-object segmentation by 2-D affine motion modeling
Abstract
A novel video-object segmentation algorithm is proposed, which takes the previously estimated 2-D dense motion vector field as input and uses the generalized recursive shortest spanning tree method to approximate each component of the motion vector field as a piecewise planar function. The algorithm is successful in capturing 3-D planar objects in the scene correctly, with acceptable accuracy at the boundaries. The proposed algorithm is fast and requires no initial guess about the segmentation mask. Moreover, it is a hierarchical scheme which gives finest to coarsest segmentation results. The only external parameter needed by the algorithm is the number of segmented regions that essentially control the level at which the coarseness the algorithm would stop. The proposed algorithm improves the “analysis model” developed in the European COST211 framework
Year
DOI
Venue
2000
10.1109/76.856454
Circuits and Systems for Video Technology, IEEE Transactions
Keywords
Field
DocType
image segmentation,image sequences,motion estimation,trees (mathematics),video signal processing,2D affine motion modeling,2D dense motion vector field,3D planar objects,European COST211 project,analysis model,coarse segmentation,cost function,fast algorithm,fine segmentation,hierarchical scheme,piecewise planar function,recursive shortest spanning tree algorithm,segmentation mask,segmented regions,video sequences,video-object segmentation algorithm
Scale-space segmentation,Computer science,Image segmentation,Artificial intelligence,Spanning tree,Motion estimation,Shortest Path Faster Algorithm,Minimum spanning tree-based segmentation,Reverse-delete algorithm,Computer vision,Ramer–Douglas–Peucker algorithm,Pattern recognition,Algorithm
Journal
Volume
Issue
ISSN
10
5
1051-8215
Citations 
PageRank 
References 
22
1.45
10
Authors
2
Name
Order
Citations
PageRank
E. Tuncel111210.93
Levent Onural211016.83