期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

一种运动估计算法的性能评估方法 被引量：1

A Performance Evaluation Method of Motion Estimation Algorithms
下载PDF
导出
摘要 同时考虑算法的精度和效率,以常用的基于梯度的运动估计算法为例,提出了一种运动估计算法的性能评估方法。在该方法中,以表征算法精度的偏差为横坐标,以表征算法效率的执行时间为纵坐标,构建了一个偏差-时间二维性能评估坐标系,通过设置算法的不同参数,绘制偏差-时间性能评估曲线。性能评估实例表明了所提出的偏差-时间性能评估方法在评估基于梯度的运动估计算法性能时的有效性。 Gradient-based algorithms for motion estimation taken as an example for evaluating performance, a performance evaluation method of motion estimation algorithms is proposed through considering accuracy as well as efficiency. In this method, the bias is used as the criterion for accuracy, and the execution time of algorithm is used as the criterion for efficiency. A two-dimension bias-time coordinate system of evaluating performance is constructed by using the bias as one coordinate and execution time as the other. The curve in this coordinate system is generated by setting different values of parameters. The examples of performance evaluation have verified the validity of the proposed approach.
作者 卢清华 张宪民 范彦斌
机构地区 佛山科技学院机电系 华南理工大学机械工程学院
出处 《工程图学学报》 CSCD 北大核心 2009年第5期113-118,共6页 Journal of Engineering Graphics
基金 国家自然科学基金资助项目(50775073) 广东省自然科学基金资助项目(8452800001000023)
关键词 计算机应用 图像处理 性能评估 运动估计 computer application image processing performance evaluation motionestimation
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献13

  • 1Barron J L, Fleet D J, Beauchemin S S. Performance of optical flow techniques [J]. International Journal of Computer Vision, 1994, 12: 43-77.
  • 2Robinson D, Milanfar P. Bias-minimizing filters for gradient-based image registration [J]. Signal Processing: Image Communication, 2005, 20:554-568.
  • 3Davis C Q, Freeman D M. Statistics of subpixel registration algorithms based on spatiotemporal gradients or block matching [J]. Opt. Eng, 1998, 37(4) 1290-1298.
  • 4Timoner S J, Freeman D M. Multi-image gradient-based algorithms for motion estimation [J]. Opt. Eng, 2001, 40(9): 2003-2016.
  • 5Liu H C, Hong T H, Herman M, et al. Accuracy vs efficiency trade-offs in optical flow algorithms [J]. Computer Vision and Image Understanding, 1998, 72 (3): 271-286.
  • 6Robinson D, Milanfar P. Fundamental performance limits in image registration [J]. IEEE Transactions on Image Processing, 2004, 9(13): 1185-1199.
  • 7Steven M K.统计信号处理基础:估计与检测理论[M].罗鹏飞等译.北京:电子工业出版社,2003.
  • 8Harry L V T. Detection, estimation, and modulation theory(英文版)[M].北京:电子工业出版社,2003.437-445.
  • 9Freeman D M, Alexander J A, Michael J G, et al. Multidimensional motion analysis using computer microvision [DB/OL]. http://umech.mit.edu/freeman/ talks/sssaw98/talk3.htm.
  • 10Barron J. tip: ftp.csd.uwo.ca [DB/OL]. 2007-11-20.

二级参考文献12

  • 1Horn B K P,Schunck B G.Determining Optical Flow[J].Artificial Intelligence,1981,17:185-203.
  • 2Horn B K P.Schunck B G.Direct Methods for Recovering Motion[J].International Journal of Computer Vision,1988,2:51-76.
  • 3Timoner S J,Freeman D M.Multi-image Gradient-Based Algorithms for Motion Estimation[J].Opt.Eng.,2001,40(9):2003-2016.
  • 4Kim Y H,Aleix M M,Kaka A C.Robust Motion Estimation under Varying Illumination[J].Image and Vision Computing,2005,23:365-375.
  • 5Farid H,Simoncelli E P.Differentiation of Discrete Multidimensional Signals[J].IEEE Transactions on Image Processing,2004,13(4):496-508.
  • 6Nestares O,Heeger D J.Robust Multiresolution Alignment of MRI Brain Volumes[J].Magnetic Resonance in Medicine,2000,43(5):705-715.
  • 7Holland P W,Welsch R E.Robust Regression Using Iteratively Reweighted Least-Squares[J].Communications in Statistics:Theory and Methods,1977,A6:813-827.
  • 8Stiller C,Konrad J.Estimating Motion in Image Sequences[J].IEEE Signal Processing Magazine,1999,16:70-91.
  • 9Robinson D,Milanfar P.Bias-Minimizing Filters Design for Gradient-based lmage Registration[J].Signal Processing:Image Communication,2005,20:554-568.
  • 10Freeman D M,Alexander J A,Michael J G,et al.Multidimensional Motion Analysis Using Computer Microvision[R].[2006-09-18].http://umech.mit.edu/freeman/talks/sssaw98/talk3.html.

共引文献1

同被引文献15

  • 1陈治,胡晓东,傅星,胡小唐.基于块匹配的MEMS平面纳米精度运动测量[J].光学精密工程,2008,16(3):505-510. 被引量：4
  • 2王涛,王晓东,王立鼎,刘冲.MEMS中微结构动态测试技术进展[J].中国机械工程,2005,16(1):83-88. 被引量：18
  • 3蒋庄德,徐通模.微纳制造技术及微系统的发展现状、趋势及展望[R/OL].装备制造(电子版),2006,2.[2009-12-22].http://www.chinaem.cn/dzkw/06-2/12.htm.
  • 4卢秉恒.微纳制造[R].北京:国家自然科学基金委员会,2004.
  • 5Timoner S J, Freeman D M. Multi- image Gradient -based Algorithms for Motion Estimation [J]. Eng., 2001,40(9): 2003-2016.
  • 6Gupta N, Kanal L. Gradient Based Image Motion Estimation without Computing Gradients[J]. International Journal of Computer Vision, 1997,22 ( 1 ) : 81-101.
  • 7Davis C Q, Freeman D M. Statistics of Subpixel Registration Algorithms Based on Spatiotemporal Gradients or Block Matching[J]. Opt. Eng. ,1998, 37(4) :1290-1298.
  • 8I.u Q H,Zhang X M. Multiscale MSE-minimizing Filters for Gradient-based Motion Estimation[J]. Measurement,2007,40 : 841-848.
  • 9Liu H C, Hong T H,Herman M,et al. Accuracy vs Efficiency Trade-offs in Optical Flow Algorithms[J]. Computer Vision and Image Understanding, 1998,72(3) : 271-286.
  • 10Horn B K P,Schunck B G. Direct Methods for Recovering Motion[J]. International Journal of Computer Vision,1988(2) : 51-76.

引证文献1

工程图学学报
2009年 第5期

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