Semantic Video Object Segmentation for Content-Based Multimedia Applications [electronic resource] /

Semantic Video Object Segmentation for Content-Based Multimedia Applications provides a thorough review of state-of-the-art techniques as well as describing several novel ideas and algorithms for semantic object extraction from image sequences. Semantic object extraction is an essential element in content-based multimedia services, such as the newly developed MPEG4 and MPEG7 standards. An interactive system called SIVOG (Smart Interactive Video Object Generation) is presented, which converts user's semantic input into a form that can be conveniently integrated with low-level video processing. Thus, high-level semantic information and low-level video features are integrated seamlessly into a smart segmentation system. A region and temporal adaptive algorithm was further proposed to improve the efficiency of the SIVOG system so that it is feasible to achieve nearly real-time video object segmentation with robust and accurate performances. Also included is an examination of the shape coding problem and the object segmentation problem simultaneously. Semantic Video Object Segmentation for Content-Based Multimedia Applications will be of great interest to research scientists and graduate-level students working in the area of content-based multimedia representation and applications and its related fields.

Saved in:
Bibliographic Details
Main Authors: Guo, Ju. author., Kuo, C.-C. Jay. author., SpringerLink (Online service)
Format: Texto biblioteca
Language:eng
Published: Boston, MA : Springer US : Imprint: Springer, 2002
Subjects:Computer science., Information storage and retrieval., Multimedia information systems., Image processing., Computer Science., Image Processing and Computer Vision., Multimedia Information Systems., Information Storage and Retrieval., Signal, Image and Speech Processing., Computer Science, general.,
Online Access:http://dx.doi.org/10.1007/978-1-4615-1503-6
Tags: Add Tag
No Tags, Be the first to tag this record!