期刊文献+

大位移变分光流计算的快速算法

Fast algorithms for large displacement variation optical flow computation
原文传递
导出
摘要 目的多尺度方法的提出解决了传统HS(Horn Schunck)算法不能计算大位移光流的问题,但同时也增加了迭代运算的步数。为加快迭代收敛速度,研究大位移变分光流计算的快速算法,并分析其性能。方法将用于加快变分图像处理迭代运算的Split Bregman方法、对偶方法和交替方向乘子法应用到大位移光流计算中。结果分别进行了精度、迭代步数、运行时间的对比实验。引入3种快速方法的模型均能够在保证精度的同时,在较少时间内计算出图像序列的光流场,所需时间为传统方法的11%~42%。结论将3种快速方法应用到大位移变分光流计算中,对于不同图像序列均可以较大地提高计算效率。 Objective The Horn-Schunck (HS) algorithm is one of the most popular optical flow estimation methods. Many scholars have proposed improved HS algorithms to improve accuracy. However, the efficiency of the HS algorithm remains an important problem because the HS algorithm requires much iterative computation. The HS algorithm is based on a differ- ential method, and it only can compute small displacement optical flow. A multi-scale method has been proposed to solve the problem that a differential method cannot compute large displacement optical flow, but the efficiency of this method is slower than before. Fast methods are studied in this research to enhance efficiency. Method In the variation image restora- tion domain, fast methods for accelerating iteration have yielded good results, and some of the fast methods have been ap- plied to small-displacement optical flow computation domain. In this study, Split Bregman method, dual method, and alter- nating direction method of multipliers are applied to large displacement optical flow computation for accelerating iteration. Result The accuracy, iteration, and time of different methods are compared quantitatively and qualitatively. The three fast methods all can obtain results with accuracy that is the same as that of the traditional method in lesser time. The time re- quired for fast algorithms is 11% - 42% of the time required for the traditional method. Conclusion Computational effi- ciency can be improved greatly by applying these three fast methods to large displacement variation optical flow computing for different image sequences.
出处 《中国图象图形学报》 CSCD 北大核心 2017年第1期66-74,共9页 Journal of Image and Graphics
基金 国家科技支撑计划项目(2014BAG03B05)~~
关键词 光流计算 大位移光流 多尺度方法 SPLIT Bregman方法 对偶方法 交替方向乘子法 optical flow computation large displacement optical flow multi-scale method Split Bregman method dual method alternating direction method of multipliers
  • 相关文献

参考文献8

二级参考文献60

  • 1危水根,陈震,黎明.基于梯度光流场计算方法的一种改进[J].计算机工程,2006,32(1):198-200. 被引量:12
  • 2杨常清,王孝通,李博,金良安.基于特征光流的角点匹配快速算法[J].光电工程,2006,33(4):85-88. 被引量:4
  • 3Horn B, Schunck B. Determining Optical Flow[J]. Artificial Intelligence, 1981, 17(1): 185-203. 被引量:1
  • 4Weickert J, Bruhn A, Brox T, et al. A Survey on Variational Optic Flow Methods for Small Displacements[M]. Berlin, Germany: Springer, 2006. 被引量:1
  • 5Bruhn A. Variational Optic Flow Computation: Accurate Model and Efficient Numerics[D]. Saarbrucken, Germany: Department of Mathematics and Computer Science, Saarland University, 2006. 被引量:1
  • 6Chambolle A. An Algorithm for Total Variation Minimization and Applications[J]. Mathematical Imaging and Vision, 2004, 20(1/2): 89-97. 被引量:1
  • 7Zach C, Pock T, Bischof H. A Duality Based Approach for Realtime TV-L1 Optical Flow[C]//Proc. of DAGM'07. Berlin, Germany: Springer, 2007. 被引量:1
  • 8Pock T, Urschler M, Zach C, et al. A Duality Based Algorithm for TV-L1-optical-flow Image Registration[C]//Proe. of the 10th International Conference on Medical Image Computing and Computer Assisted Intervention. NY, USA: [s. n.], 2007. 被引量:1
  • 9Li Yingying, Osher S. A New Median Formula with Applications to PDE Based Denoising[J]. Commun. Math. Sci., 2009, 7(3): 741. 被引量:1
  • 10Li L, Luo R. Context-controlled adaptive background subtraction [EB/OL].[ 2009-12- 3 ]. http://www, cvg. rdg. ac. uk/ PETS2OO6/PETS2006_PROCEEDIN GS. pdf. 被引量:1

共引文献111

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