计算机应用 ›› 2010, Vol. 30 ›› Issue (12): 3265-3268.

• 图形图像处理 • 上一篇    下一篇

基于熵能的H.264压缩域运动对象分割

张文琪1,张茂军2,李乐2,李永乐2   

  1. 1. 国防科学技术大学五院系统工程系五室
    2. 国防科学技术大学信息系统与管理学院
  • 收稿日期:2010-06-04 修回日期:2010-07-17 发布日期:2010-12-22 出版日期:2010-12-01
  • 通讯作者: 张文琪
  • 基金资助:
    国家高技术研究发展计划(863计划);基于图形处理器的高性能计算;基于图形处理器的高性能计算

Video object segmentation in H.264 compressed domain based on entropy energy

  • Received:2010-06-04 Revised:2010-07-17 Online:2010-12-22 Published:2010-12-01

摘要: 提出了一种基于熵能选取自适应阈值的时空域运动对象分割方法。首先对H.264压缩码流中提取的原始运动矢量场进行连续多帧的累加来增强运动信息,并对累积运动矢量场进行相似性判断,初步获得运动块;然后提取压缩码流中4×4块残差编码位数,并基于熵能自动选取自适应局部阈值,获取运动区域的轮廓信息;最后结合运动块和轮廓信息按照一定的规则对边界进行校正。对多个视频序列进行了实验,结果表明,该算法能快速取得较好的分割结果。

关键词: H.264, 运动矢量场, 残差编码位数, 熵能, 对象分割

Abstract: The paper presented a new temporal-spatial method for moving object segmentation in H.264 based on local self-adaptive threshold on entropy. The Motion Vector (MV) fields of several continuous frames were accumulated to enhance the motion information. Then the similarity measure was performed on the accumulated MV field to remove part of noise. And then residual size of 4×4 block was extracted from the compressed bitstream, and each 4×4 block threshold was selected by local self-adaptive threshold on entropy. Finally according to some formula, the article ulteriorly refine the boundary of the motion block. The H.264 sequences test demonstrates the validity of the proposed method.

Key words: H.264, Motion Vector (MV) field, coded residual bits, entropy energy, object segmentation