期刊文献+

最大距离预测法在超长时间精子序列图像跟踪中的应用 被引量:2

The Maximum Distance Prediction Method Applied to the Super Long Time Sperm Image Sequence Tracking
下载PDF
导出
摘要 精子质量的优劣是评价男性生殖能力的重要指标.根据世界卫生组织(WHO)人类精液检查与处理实验室手册第5版可知,对精子序列图像进行超长时间跟踪可以更精确地分析精子的质量.本文根据精子运动的特点,提出一种基于小窗口的应用于超长时间精子序列图像跟踪的最大距离预测法.该方法可跟踪精子在每一帧的轨迹点,然后把这些轨迹点坐标连在一起就是精子的运动轨迹.试验结果表明:该方法可以快速、准确、稳定地实时跟踪精子. Sperm quality is an important index of male reproductive ability. Acrroding to the request of laboratory manual version 5 of human semen examination and processing from the world health or- ganization (WHO), a method of ultra-long time tracking on sperm sequence images can more accu- rately analyze the quality of sperm. According to the characteristics of sperm moving target, we pr- esent a method of the maximum distance prediction based on a small window to track ultra-long time sperm sequence images. By tracking sperm track points of each frame, then putting these track point coordinates together ,the trajectory of sperm is obtained. Experimental results show that the method can fastly, accurately and stably conduct the real-time tracking of sperm.
出处 《测试技术学报》 2014年第2期132-136,共5页 Journal of Test and Measurement Technology
关键词 序列图像 超长时间 最大距离预测 最近邻搜索 实时跟踪 image sequence super long time the maximum distance prediction nearest neighbor search real-time tracking
  • 相关文献

参考文献9

二级参考文献40

共引文献93

同被引文献19

  • 1Ding T,Sznaier M,Camps O.Fast track matching and event detection[C]//Anchorage:the IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
  • 2Collins R.Multi-target data association with higher-order motion models[C]//Providence:the IEEE Conference on Computer Vision and Pattern Recognition,2012:1744-1751.
  • 3Andriyenko A,Schindler K,Roth S.Discrete-continuous optimization for multi-target tracking[C]//Providence:the IEEE Conference on Computer Vision and Pattern Recognition,2012:1926-1933.
  • 4Caglayan D,Mario S,Octavia C.The way they move:tracking multiple targets with similar appearance[C]//IEEE International Conference on Computer Vision,2013:2304-2311.
  • 5Ross G,Soland R.A branch and bound algorithm for the generalized assignment problem[J].Mathematical Programming,1975,8(1):91-103.
  • 6Shmoys D,Tardos E.An approximation algorithm for the generalized assignment problem[J].Mathematical Programming,1993,62(1):461-474.
  • 7Gold S,Rangarajan A.Softmax to softassign:neural network algorithms for combinatorial optimization[J].Journal of Artificial Neural Networks,1995,2(4):381-399.
  • 8Breiman L.Hinging hyperplanes for regression,classification and function approximation[C]//IEEE Transaction on Information Theory,1993:999-1011.
  • 9Park H,Zhang L,Rosen J B.Low rank approximation of a Hankel matrix by structured total least norm[J].BIT Numerical Mathematics,1999,39(4):757-779.
  • 10Markovsky I,Huffel S V.Overview of total least squares methods[J].Signal Processing,2007,87(10):2283-2302.

引证文献2

二级引证文献3

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