作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2009, Vol. 35 ›› Issue (3): 235-236,. doi: 10.3969/j.issn.1000-3428.2009.03.080

• 多媒体技术及应用 • 上一篇    下一篇

基于鲁棒M-估计器的全局运动估计方法

黄官远,严 晖   

  1. (中南大学信息科学与工程学院,长沙 410083)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-02-05 发布日期:2009-02-05

Method for Global Motion Estimation Based on Robust M-estimator

HUANG Guan-yuan, YAN Hui   

  1. (School of Information Science and Engineering, Central South University, Changsha 410083)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-02-05 Published:2009-02-05

摘要: 提出一种改进的基于鲁棒M-估计器的全局运动估计方法,在图像像素残差上采用在统计上鲁棒的M-估计目标函数,引入简化的像素残差权值函数作为二值函数,改进了全局运动估计中去除噪声点的方法。实验结果表明,改进算法的运动精度高,对大多数的图像序列都有较好鲁棒性且计算量小。

关键词: 全局运动估计, M-估计器, 鲁棒性

Abstract: This paper proposes an improved method based on robust M-estimator for global motion. The algorithm adopts statistically robust M-estimator target function on image pixel residual, weighted-function is simplified as binary function. It improves the method of elimination noise points. Experimental results show that the improved algorithm can get high precision and robust with various image sequence, and attain computationally saving.

Key words: global motion estimation, M-estimator, robust

中图分类号: