Image sequence analysis for emerging interactive multimedia services - TheEuropean COST 211 framework

Citation
Aa. Alatan et al., Image sequence analysis for emerging interactive multimedia services - TheEuropean COST 211 framework, IEEE CIR SV, 8(7), 1998, pp. 802-813
Citations number
40
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN journal
10518215 → ACNP
Volume
8
Issue
7
Year of publication
1998
Pages
802 - 813
Database
ISI
SICI code
1051-8215(199811)8:7<802:ISAFEI>2.0.ZU;2-D
Abstract
Flexibility and efficiency of coding, content extraction, and content-based search are key research topics in the field of interactive multimedia. Ong oing ISO MPEG-4 and MPEG-7 activities are targeting standardization to faci litate such services. European COST Telecommunications activities provide a framework for research collaboration. COST 211(bis) and COST 211(ter) acti vities have been instrumental in the definition and development of the ITU- T H.261 and H.263 standards for video-conferencing over ISDN and videophony ol er regular phone lines, respectively. The group has also contributed si gnificantly to the ISO MPEG-4 activities. At present a significant effort o f the COST 211(ter) group activities is dedicated toward image and video se quence analysis and segmentation-an important technological aspect for the success of emerging object-based MPEG-4 and MPEG-7 multimedia applications. The current work of COST 211 is centered around the test model, called the Analysis Model (AM), The essential feature of the AM is its ability to fus e information front different sources to achieve a high-quality object segm entation. The current information sources are the intermediate results from frame-based (still) color segmentation, motion vector based segmentation, and change-detection-based segmentation. Motion vectors, which form the bas is for the motion vector based intermediate segmentation, are estimated fro m consecutive frames. A recursive shortest spanning tree (RSST) algorithm i s used to obtain intermediate color and motion vector based segmentation re sults. A rule-based region processor fuses the intermediate results; a post processor further refines the final segmentation output. The results of the current AM are satisfactory; it is expected that there will be further imp rovements of the AM within the COST 211 project.