首页 | 本学科首页   官方微博 | 高级检索  
     

结合时空信息的视频对象平面自动提取算法
引用本文:杨文明,刘济林,王其聪.结合时空信息的视频对象平面自动提取算法[J].计算机辅助设计与图形学学报,2006,18(6):865-869.
作者姓名:杨文明  刘济林  王其聪
作者单位:浙江大学信息科学与电子工程系,杭州,310027
摘    要:提出一种视频对象平面自动提取算法,首先以时域帧间运动信息为依据,利用高斯检验方法得到初始的二值运动模板,并建立双尺度邻域的MRF模型进一步检验,以获取平滑、完整的运动模板;然后提出了结合非线性变换的改进分水岭算法对运动区域进行帧内空域分割;最后对时域和空域分割结果进行比重运算,提取最终运动对象.实验结果说明了该算法的有效性.

关 键 词:视频对象平面  高斯检验  双尺度邻域  MRF模型  分水岭算法  比重运算
收稿时间:2005-06-20
修稿时间:2005-11-09

Automatic Extraction of Video Object Plane by Integrating Spatio-Temporal Information
Yang Wenming,Liu Jilin,Wang Qicong.Automatic Extraction of Video Object Plane by Integrating Spatio-Temporal Information[J].Journal of Computer-Aided Design & Computer Graphics,2006,18(6):865-869.
Authors:Yang Wenming  Liu Jilin  Wang Qicong
Abstract:An automatic video object plane extraction algorithm is proposed. At first, a binary moving mask is obtained by Gaussianity test based on temporal motion information, followed by a further test by establishing MRF model on double-scale neighborhood to achieve smooth and complete binary moving mask. Then, an improved watershed algorithm based on nonlinear transform is employed to segment moving regions. Finally, moving objects are extracted by performing ratio operation on spatial and temporal results. Experimental results validate the proposed algorithm.
Keywords:video object plane  Gaussianity test  double-scale neighborhood  MRF model  watershed algorithm  ratio operation
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号