Paper Info
Title
Automatic non-interactive matting of dynamic targets in complex video using Graph Cuts.
Abstract
Extracting moving targets from video automatically and accurately is of great significance in the field of intelligent transport. This paper is devoted to the video object matting problem which is based on solving an optimization problem. The matting problem is severely ill-posed and generally cannot be solved without any extra constraints. In contrast to previous efforts, we develop a new method of automatic non-interactive matting of dynamic objects in complex video. Combining the Orthogonal Gaussian-Hermite Moments algorithm and Graph Cuts, highly stabile scribbles become automatic generation without interaction in the method and are used as the extra constraints in calculating the minimum energy function. The real-time of moving object matting may be improved obviously. Experiments demonstrate that the proposed method can effectively extract moving targets from video in a real-time way. And the method can be widely applied and suited to the extraction of complex video images due to the robustness of these scribbles. © 2012 Springer-Verlag.
Year
DOI
Venue
2013
10.1007/s13042-012-0123-7
Int. J. Machine Learning & Cybernetics
Keywords
Field
DocType
digital matting,generation mask,graph cuts,orthogonal gaussian-hermite moments,Digital matting,Orthogonal Gaussian–Hermite moments,Generation mask,Graph Cuts
Cut,Computer vision,Computer science,Robustness (computer science),Artificial intelligence,Optimization problem
Journal
Volume
Issue
ISSN
4
6
1868808X
Citations 
PageRank 
References 
0
0.34
17
Authors
2
Name
Order
Citations
PageRank
Yu Zhou1396.37
Jinbang Xu2157.44