Video Object Extraction and Representation: Theory and Applications / Edition 1

by I-Jong Lin, S.Y. Kung

Overview

“If you have built castles in the air, your work need not be lost; that is where they should be. Now put the foundations under them. ” - Henry David Thoreau, Walden Although engineering is a study entrenched firmly in belief of pr- matism, I have always believed its impact need not be limited to pr- matism. Pragmatism is not the boundaries that define engineering, just the (sometimes unforgiving) rules by which we sight our goals. This book studies two major problems of content-based video proce- ing for a media-based technology: Video Object Plane (VOP) Extr- tion and Representation, in support of the MPEG-4 and MPEG-7 video standards, respectively. After reviewing relevant image and video processing techniques, we introduce the concept of Voronoi Ordered Spaces for both VOP extraction and representation to integrate shape infor- tion into low-level optimization algorithms and to derive robust shape descriptors, respectively. We implement a video object segmentation system with a novel surface optimization scheme that integrates Voronoi Ordered Spaces with existing techniques to balance visual information against predictions of models of a priori information. With these VOPs, we have explicit forms of video objects that give users the ability to - dress and manipulate video content. We outline a general methodology of robust data representation and comparison through the concept of complex partitioning mapped onto Directed Acyclic Graphs (DAGs).

Product Details

ISBN-13:	9780792379744
Publisher:	Springer US
Publication date:	09/30/2000
Series:	The Springer International Series in Engineering and Computer Science , #584
Edition description:	2002
Pages:	177
Product dimensions:	6.10(w) x 9.25(h) x 0.02(d)

Table of Contents

to Content-Based Visual Processing.- Existing Techniques of Visual Processing.- Voronoi Ordered Space.- A System for Video Object Segmentation.- Robust Representation of Shape with DAGs.- A System for Image/Video Object Query by Shape.- The Future of Content-Based Video Processing.

Editorial Reviews

Working to establish a computational infrastructure for content-based video processing for a media-based technology, Lin, in private industry, and Kung (Princeton U.) look at the two problems of extracting objects from a video plane and representing them there for later extraction. After reviewing relevant image and video processing techniques, they introduce the concept of Voronoi Ordered Spaces to integrate shape information into low-level optimized algorithms and to derive robust shape descriptors, for the two problems respectively. They implement a video object segmentation system with a novel surface optimization scheme that integrates the Voronoi Ordered Spaces with existing techniques to balance visual information against predictions of models of information. Annotation c. Book News, Inc., Portland, OR (booknews.com)

Booknews