Record Details

DWT based hierarchical video segmentation

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title DWT based hierarchical video segmentation
 
Creator VENKATESWARAN, SUNDER
DESAI, UB
 
Subject discrete wavelet transforms
image colour analysis
image segmentation
image sequences
least squares approximations
multimedia computing
video coding
 
Description To provide multimedia applications with new functionalities, such as content-based interactivity and scalability, the new video coding standard, MPEG-4 relies on content-based representation. This means a prior decomposition of a video sequence into semantically meaningful, physical objects. We develop a fast yet robust color segmentation algorithm based on DWT and k-means clustering. After spatial segmentation, a dense optical flow field is estimated for the whole image, using which a motion parameter model is estimated for each region using a least squares technique. Adjacent regions with a coherent motion are then merged together to form moving objects. This leads to segmented video.
IEEE & CAS
 
Publisher IEEE
 
Date 2008-12-15T10:54:08Z
2011-11-27T14:06:34Z
2011-12-15T09:56:33Z
2008-12-15T10:54:08Z
2011-11-27T14:06:34Z
2011-12-15T09:56:33Z
2002
 
Type Article
 
Identifier Proceedings of the IEEE International Symposium on Circuits and Systems (V 3), Scottsdale, USA, 26-29 May 2002, III-815-III-818
0-7803-7448-7
http://hdl.handle.net/10054/332
http://dspace.library.iitb.ac.in/xmlui/handle/10054/332
 
Language en