期刊文献+

基于时空融合的视频对象分割

在线阅读 下载PDF
导出
摘要 算法利用高斯混合模型对空间属性进行聚类分割,选取合适的初始参数通过k-means聚类和EM算法估计参数,并对EM算法进行适当改进,提高视频对象的分割速度。同时利用多帧间差法在时域中获取运动模板,通过聚类信息与运动模板进行匹配,获得最终的分割对象。实验表明,可以获得较好的分割效果,同时分割速率也有一定的提高。
作者 文聪
出处 《机电技术》 2010年第4期30-32,共3页 Mechanical & Electrical Technology
  • 相关文献

参考文献6

二级参考文献31

  • 1MPEG Video Group. Overview of the MPEG-4standard[S]. ISO/IEC JTC1/SC29/WG11 N4668. 2002.
  • 2Zhang D S, Lu G J. Segmentation of moving objects in image sequences: a review[J]. Circuits, Systems, and Signal Processing, 2001,20(2): 143~183.
  • 3Mech R, Wollborn M. A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera[J]. Signal Processing, 1998, 66(2): 203~217.
  • 4Aach T, Kaup A, Mester R. Statistical model-based change detection in moving video[J]. Signal Processing, 1993, 31(2): 165~180.
  • 5Ziliani F, Cavallaro A. Image analysis for video sur-veillance based on spatial regularization of a statistical model-based change detection[J]. Real-Time Imaging, 2001, 7(5): 389~399.
  • 6Horn B K P, Schunck B G. Determining optical flow[J]. Artificial Intelligence, 1981, 17: 185~203.
  • 7Bierling M. Displacement estimation by hierarchical block matching[A]. Proc SPIE Visual Communications and Image Processing, VCIP[C]. USA: Cambridge, MA, 1988,1001: 942~951.
  • 8Ma K K, Wang H Y. Region-based nonparametric optical flow segmentation with pre-clustering and post-clustering[A]. IEEE International Conference on Multimedia and Expo,ICME[C]. Switzerland: Lausanne, 2002, 2: 201~204.
  • 9Meier T, Ngan K N. Video segmentation for con-tent-based coding[J]. IEEE Trans Circuits and Systems for Video Technology, 1999, 9(8): 1190~1203.
  • 10Hsu C T, Tsan Y C. Mosaics of video sequences with moving objects[A]. IEEE International Conference on Image Processing, ICIP[C]. Greece: Thessaloniki, 2001, 2: 387~390.

共引文献121

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部