The Production of Ground Truths for Evaluating Highly Accurate Stereovision Algorithms
Tristan Dagobert
→ BibTeX
@article{ipol.2018.187,
    title   = {{The Production of Ground Truths for Evaluating Highly Accurate Stereovision Algorithms}},
    author  = {Dagobert, Tristan},
    journal = {{Image Processing On Line}},
    volume  = {8},
    pages   = {1--23},
    year    = {2018},
    doi     = {10.5201/ipol.2018.187},
}
% if your bibliography style doesn't support doi fields:
    note    = {\url{https://doi.org/10.5201/ipol.2018.187}}
published
2018-01-02
reference
Tristan Dagobert, The Production of Ground Truths for Evaluating Highly Accurate Stereovision Algorithms, Image Processing On Line, 8 (2018), pp. 1–23. https://doi.org/10.5201/ipol.2018.187

Communicated by Carlo de Franchis

Abstract

The conception and improvement of algorithms for subpixel stereovision requires very precise test databases. The state of the art on the sets of images used extensively by the scientific community shows that they are often incomplete and imprecise compared to the dataset goals. We will present a method based on image synthesis to produce stereoscopic pairs with ground truths such as disparity and occlusion maps reaching an accuracy of about 1e-6 pixels. The a priori noise estimate is also taken into account. This process allows us to deliver a new image database consisting of 66 stereo pairs together with their ground truths.

Download

Supplementary Materials

Available datasets (described in the manuscript):