Semantic Video Object Segmentation for Content-Based Multimedia Applications

by Guo, Ju; Kuo, C. C. Jay

• ISBN13: 9780792375135
• ISBN10: 0792375130
• Format: Hardcover
• Copyright: 2001-08-01
• Publisher: Springer Verlag

Summary

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.

Table of Contents

List of Figures	ix
List of Tables	xiii
Preface	xv
Acknowledgments	xix
Introduction	1	(8)
Significance of the Research	1	(1)
Background of the Research	2	(2)
Contributions of the Research	4	(2)
Color Feature	4	(1)
Automatic Segmentation Algorithm	4	(1)
Interactive Semantic Object Segmentation	5	(1)
Temporal and Region-adaptive Processing	6	(1)
Object Shape Postprocessing	6	(1)
Outline of the Monograph	6	(3)
Review of Previous Work	9	(20)
Change Detection	9	(2)
Motion Segmentation	11	(4)
Motion Model	11	(3)
Previous Work in Motion Segmentation	14	(1)
Spatial and Temporal Segmentation	15	(5)
Spatial Segmentation Techniques	15	(2)
Three Segmentation Proposals in MPEG4	17	(1)
Other Combinations of Spatial and Temporal Segmentation	18	(2)
User Interactive Segmentation	20	(6)
Motivation	20	(1)
Category of User Interaction	21	(1)
Efficiency of User Interaction	22	(1)
Previous Work	23	(3)
Evaluation of Segmentation Quality	26	(3)
Automatic Segmentation	29	(16)
Video Segmentation With Color and Motion	29	(2)
Color-based Spatial Segmentation	31	(1)
Motion Tracking and Spatial-Temporal Integration	32	(3)
Experimental Results	35	(10)
Subjective Evaluation	35	(1)
Objective Evaluation	36	(9)
Object Shape Postprocessing	45	(8)
Proposed Algorithm for Coding Optimization	45	(1)
Shape Coding Optimization	46	(1)
Experimental Results	47	(6)
Interactive Segmentation Algorithms	53	(22)
Description of the SIVOG System	54	(10)
System Overview	54	(1)
User Interface	55	(1)
Smart-processing Kernel	56	(1)
Temporal Tracking of Rigid Objects	57	(2)
Boundary Update for Non-rigid Objects	59	(4)
User Correction and Update	63	(1)
System Evaluation	64	(1)
Experimental Results	64	(11)
Rigid Object Segmentation	64	(2)
Non-rigid Object Segmentation	66	(9)
Temporal and Spatial Adaptive Processing	75	(20)
Introduction	75	(1)
Description of the SIVOG System	76	(3)
Semantic User Interaction	76	(1)
Smart Processing Kernel	76	(3)
Region and Temporal Adaptive Processing	79	(8)
Region Selection	79	(3)
Temporal Skipping and Interpolation	82	(5)
Experimental Results	87	(8)
System Efficiency	87	(1)
System Accuracy	88	(7)
Summary and Future Work	95	(4)
Future Work	96	(3)
Texture Segmentation	96	(1)
Model-based Segmentation Algorithm	96	(1)
Object Postprocessing	96	(1)
Evaluation of User's Effort	97	(2)
References	99	(8)
About the authors	107	(2)
Index	109