期刊文献+

全局运动多分辨率光流估计算法的改进与实现 被引量:1

Improvement and Implementation of Global Motion Multi-resolution Optical Flow Estimation Algorithm
下载PDF
导出
摘要 为了提高低分辨率图像之间的位移估计精度,在传统光流算法的基础上,提出了全局运动的多分辨率光流估计算法.实验结果表明:该算法能够快速实现小位移和准确的实现大位移的运动估计,通过对互有亚像素位移的多帧低分辨率图像对比相位相关法进行运动估计,改进的多分辨率光流估计算法实现的高精度亚像素位移误差精度为0.05pi. In order to improve the estimation precision of displacement among low resolution images,the paper proposes an optical flow estimation algorithm of global motion with multi-resolution,based on the traditional optical flow algorithm.The experimental results shows that the algorithm can realize fast small displacement motion estimation and accurate big displacement motion estimation.The estimation is implemented for images of low resolution with sub-pixel displacement,compared with correlation phase estimation.The results show that this improved algorithm achieves high precision pixel displacement estimation and the precision reaches 0.05pi.
作者 韩军 张东
出处 《西安工业大学学报》 CAS 2011年第2期115-119,共5页 Journal of Xi’an Technological University
关键词 光流估计算法 多分辨率 亚像素估计 相位相关法 optical flowesti mation algorithm multi-resolution sub-pixel esti mation phase correlation method
  • 相关文献

参考文献11

  • 1Park S C,Park M K,Kang M G.Super-resolution Image Reconstruction-a Technical Overview[J].IEEE Signal Processing Magazine,2003,20(3):21.
  • 2Ng M K,Bose N K.Mathematical Analysis of Superresolution Methodology[J].IEEE Signal Processing Magazine,2003,20 (3):62.
  • 3Irani M,Peleg S.Improving Resolution by Image Registration[C]//CVGIP:Graphical Models and Image,1991,53(3):231.
  • 4Huang Y,Ma S,Shen C.Predictive Line Search:An Efficient Motion Estimation Algorithm for MPEG-4 Encoding Systems on Multimedia Processors[J].IEEE Trans on Circuits and Systems for Video Technology,2003,13 (1):111.
  • 5HORNB,SCHUCK B.Determining Optical Flow[J].Artificial Intelligence,1981,17(4):185.
  • 6Barron J,Fleet D,Besuchemin S.Performance of Optical Flow Techniques[J].International Journal of Computer Vision,1994,12(1):42.
  • 7Black M J,Yacoob Y,Jepson A D,et al.Learning Parameterized Models of Image Motion[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR97),1997:561.
  • 8ZUCCHELLI M.Optical Flow Based Structure from Motion[M/OL].CVAP Lab.Royal Institute of Technology,Stockholm,2002[2007-09-23].http://citeseerx.ist.psu.edu/viewdoc/download? doi=10.1.1.12.5862&rep= rep1 &type= pdf.
  • 9段智勇,王庆康.新型纳米分辨率位移定位平移台的研制[J].纳米技术与精密工程,2005,3(3):177-180. 被引量:5
  • 10Haussecker H,Fleet D.Computing Optical Flow with Physical Models of Brightness Variation[J].IEEE TPAMI,2001,23(6):661.

二级参考文献14

共引文献21

同被引文献8

引证文献1

二级引证文献1

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