Video Object Extraction and Representation

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.

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

Booknews

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)