Multidimensional directional steerable filters — Theory and application to 3D flow estimation

作者：

Highlights：

• Multi-dimensional motion estimation is studied in the frequency domain.

• Theoretical analysis on the construction of multi-dimensional steerable filters

• Analysis on the use of steerable filters in the dense 3D flow estimation task

• Formulation of a steerable filter-based algorithm for 3D flow estimation

摘要

•Multi-dimensional motion estimation is studied in the frequency domain.•Theoretical analysis on the construction of multi-dimensional steerable filters•Analysis on the use of steerable filters in the dense 3D flow estimation task•Formulation of a steerable filter-based algorithm for 3D flow estimation

论文关键词：Steerable filters,Multi-dimensional signal processing,Frequency domain,3D flow estimation

论文评审过程：Received 10 July 2015, Revised 15 September 2017, Accepted 10 January 2018, Available online 31 January 2018, Version of Record 9 March 2018.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.01.002