| 在视频对象平面生成中使用细胞神经网络进行初始对象的分割 |
| |
| 引用本文： | 王慧,杨高波,张兆扬.在视频对象平面生成中使用细胞神经网络进行初始对象的分割[J].上海大学学报(英文版),2003,7(2):168-172. |
| |
| 作者姓名： | 王慧 杨高波 张兆扬 |
| |
| 作者单位： | SchoolofCommunicationandInformationEngineering，SchoolofCommunicationandInformationEngineering，SchoolofCommunicationandInformationEngineering ShanghaiUniversity，Shanghai200072，China，ShanghaiUniversity，Shanghai200072，China，ShanghaiUniversity，Shanghai200072，China |
| |
| 基金项目： | ProjectsupportedbytheNationalNatureScienceFoundationofChina(GrantNo .60 172 0 2 0 ) |
| |
| 摘 要： | 1 Introduction MPEG 4videocodingstandard providesobject basedfunctionalitiesbyintroducingtheconceptofvideoobject plane (VOP) .Withtheextractionofvideoobjectsandallocatingdifferentnumberofbitsordifferentframe ratesfordifferentobjects ,thestan dardcansupportobject basedscalabilitythatisusefulinmanypracticalapplications1] .However,MPEG 4alwaysassumesthatthevideocontentstobecodedarewellrepresentedinvideoobjectswithoutmandatinganyspecifictechniques;sovideoobjectsegmentationbecomesanimportant…
|
| 关 键 词： | 图像编码 视频分割 细胞式神经网络 MPEG－4 视频序列 |
| 收稿时间： | 1 July 2002 |
Initial object segmentation for video object plane generation using cellular neural networks |
| |
| Wang?Hui,Yang?Gao-Bo,Zhang?Zhao-Yang.Initial object segmentation for video object plane generation using cellular neural networks[J].Journal of Shanghai University(English Edition),2003,7(2):168-172. |
| |
| Authors: | Wang Hui Yang Gao-Bo Zhang Zhao-Yang |
| |
| Institution: | School of Communication and Information Engineering, Shanghai University, Shanghai 200072, China |
| |
| Abstract: | MPEG 4 is a basic tool for interactivity and manipulation of video sequences. Video object segmentation is a key issue in defining the content of any video sequence, which is often divided into two steps: initial object segmentation and object tracking. In this paper, an initial object segmentation method for video object plane(VOP) generation using color information is proposed. Based on 3 by 3 linear templates, a cellular neural network (CNN) is used to implemented object segmentation. The Experimental results are presented to verify the efficiency and robustness of this approach. |
| |
| Keywords: | video object plane(VOP) cellular neural networks(CNN) templates |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
