A Line Search Multilevel Truncated Newton Algorithm for Computing the Optical Flow
Lluís Garrido, El Mostafa Kalmoun
published
2015-06-19
reference
Lluís Garrido, and El Mostafa Kalmoun, A Line Search Multilevel Truncated Newton Algorithm for Computing the Optical Flow, Image Processing On Line, 5 (2015), pp. 124–138. https://doi.org/10.5201/ipol.2015.112

Communicated by Enric Meinhardt-Llopis
Demo edited by Enric Meinhardt-Llopis

Abstract

We describe the implementation details and give the experimental results of three optimization algorithms for dense optical flow computation. In particular, using a line search strategy, we evaluate the performance of the unilevel truncated Newton method (LSTN), a multiresolution truncated Newton (MR/LSTN) and a full multigrid truncated Newton (FMG/LSTN). We use three image sequences and four models of optical flow for performance evaluation. The FMG/LSTN algorithm is shown to lead to better optical flow estimation with less computational work than both the LSTN and MR/LSTN algorithms.

Download