Paper Info
Title
Adaptable Neural Networks for Unsupervised Video Object Segmentation of Stereoscopic Sequences
Abstract
An adaptive neural network architecture is proposed in this paper, for efficient video object segmentation and tracking in stereoscopic sequences. The scheme includes: (A) A retraining algorithm that optimally adapts the network weights to the current conditions and simultaneously minimally degrades the previous network knowledge. (B) A semantically meaningful object extraction module for constructing the retraining set of the current conditions and (C) a decision mechanism, which detects the time instances when network retraining is required. The retraining algorithm results in the minimization of a convex function subject to linear constraints. Furthermore description of the current conditions is achieved by appropriate combination of color and depth information. Experimental results on real life video sequences indicate the promising performance of the proposed adaptive neural network-based video object segmentation scheme.
Year
DOI
Venue
2001
10.1007/3-540-44668-0_147
ICANN
Keywords
Field
DocType
semantically meaningful object extraction,efficient video object segmentation,network weight,current condition,algorithm result,real life video sequence,proposed adaptive neural,stereoscopic sequences,video object segmentation scheme,adaptable neural networks,adaptive neural network architecture,unsupervised video object segmentation,previous network knowledge,convex function
Computer science,Image segmentation,Minification,Artificial intelligence,Artificial neural network,Computer vision,Video production,Pattern recognition,Stereoscopy,Segmentation,Convex function,Convex optimization,Machine learning
Conference
Volume
ISSN
ISBN
2130
0302-9743
3-540-42486-5
Citations 
PageRank 
References 
0
0.34
9
Authors
4
Name
Order
Citations
PageRank
Anastasios D. Doulamis188393.64
Klimis S. Ntalianis26615.74
Nikolaos Doulamis369180.72
Stefanos Kollias42268229.16