Automatic MPEG-4 sprite coding-Comparison of integrated object segmentation algorithms

作     者：Glantz, Alexander Krutz, Andreas Sikora, Thomas Nunes, Paulo Pereira, Fernando 

作者机构：Tech Univ Berlin Commun Syst Grp Berlin Germany Inst Super Ciencias Trabalho & Empresa Inst Telecommun Lisbon Portugal Inst Super Tecn Inst Telecommun Lisbon Portugal 

出 版 物：《MULTIMEDIA TOOLS AND APPLICATIONS》 (多媒体工具和应用)

年 卷 期：2010年第49卷第3期

页      面：483-512页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：MPEG-4 Visual Global motion estimation Background modeling Object segmentation Sprite coding 

摘      要：Sprite coding, as standardized in MPEG-4 Visual, can result in superior performance compared to common hybrid video codecs. We consider sprite coding, which significantly increases the objective as well as the subjective quality of coded video content. The main challenge of this approach is the segmentation of the foreground objects in a preprocessing step. We evaluate automatic object segmentation methods based on global motion estimation and background sprite generation. The objects are coded using the MPEG-4 Visual Main Profile and compared with the Advanced Simple Profile.