Comparison of Optical Flow Methods under Stereomatching with Short Baselines
Tristan Dagobert, Nelson Monzón, Javier Sánchez
→ BibTeX
@article{ipol.2019.217,
    title   = {{Comparison of Optical Flow Methods under Stereomatching with Short Baselines}},
    author  = {Dagobert, Tristan and Monzón, Nelson and Sánchez, Javier},
    journal = {{Image Processing On Line}},
    volume  = {9},
    pages   = {329--359},
    year    = {2019},
    doi     = {10.5201/ipol.2019.217},
}
% if your bibliography style doesn't support doi fields:
    note    = {\url{https://doi.org/10.5201/ipol.2019.217}}
published
2019-10-09
reference
Tristan Dagobert, Nelson Monzón, and Javier Sánchez, Comparison of Optical Flow Methods under Stereomatching with Short Baselines, Image Processing On Line, 9 (2019), pp. 329–359. https://doi.org/10.5201/ipol.2019.217

Communicated by Gabriele Facciolo
Demo edited by Nelson Monzón and Tristan Dagobert

Abstract

This article studies the effectiveness of optical flow methods applied to short baseline image pairs under different noise levels. New metrics have been developed to analyze the results because the usual metrics are inadequate in a subpixel context. We have used the implementation of some standard optical flow methods adapted to the stereo problem. Our experiments show that the Brox et al. method produces the least errors, with a 60% success rate and a relative precision at 1/100th of a pixel. On the other hand, our comparison shows that a discontinuity preserving method, derived from Brox et al., also provides competitive results at the same time that it yields disparities with more details and correct contours.

Download

Non-Reviewed Supplementary Materials

These files and information are provided by the authors and have not been reviewed.