Title

Ensemble Classifier
for Combining Stereo Matching Algorithms

Stereo Matchers and Features




The objective of our research is to test the hypothesis that a competitive stereo matching system can be constructed by combining multiple stereo matching algorithms in a principled way without requiring domain expertise from the users.

We designed a classifier ensemble that select among multiple candidate disparities for each pixel using a technique to select which of the over 100 available matchers to use as inputs to the classifiers.

Stereo Matchers

SAD, SSD, Sobel, XNCC, SNCC, Censues, Shiftable Windows, MRF, rSGM, FCVF, ELAS, DAISY, Superpixels.

Features

Distance from Disccontinuity, Left-Right Consistency.

BibTeX

inproceedings {spyr15_3dv,
title = {Ensemble Classifier for Combining Stereo Matching Algorithms},
author = {Spyropoulos, Aristotle and Mordohai, Philippos},
booktitle = {International Conference on 3D Vision (3DV)},
year = {2015}
}

Back