Video Object Extraction and Representation: Theory and Applications: 584 (The Springer International Series in Engineering and Computer Science) - Tapa dura

“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 p- cessing 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).

Video Object Extraction and Representation: Theory and Applications is an essential reference for electrical engineers working in video; computer scientists researching or building multimedia databases; video system designers; students of video processing; video technicians; and designers working in the graphic arts.
In the coming years, the explosion of computer technology will enable a new form of digital media. Along with broadband Internet access and MPEG standards, this new media requires a computational infrastructure to allow users to grab and manipulate content. The book reviews relevant technologies and standards for content-based processing and their interrelations. Within this overview, the book focuses upon two problems at the heart of the algorithmic/computational infrastructure: video object extraction, or how to automatically package raw visual information by content; and video object representation, or how to automatically index and catalogue extracted content for browsing and retrieval. The book analyzes the designs of two novel, working systems for content-based extraction and representation in the support of MPEG-4 and MPEG-7 video standards, respectively.
Features of the book include:

• Overview of MPEG standards;
• A working system for automatic video object segmentation;
• A working system for video object query by shape;
• Novel technology for a wide range of recognition problems;
• Overview of neural network and vision technologies

Video Object Extraction and Representation: Theory and Applications will be of interest to research scientists and practitioners working in fields related to the topic. It may also be used as an advanced-level graduate text.