Evaluation of stereo confidence indoors and outdoors

Xiaoyan Hu, Philippos Mordohai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

48 Scopus citations

Abstract

We present an extensive evaluation of 13 confidence metrics for stereo matching that compares the most widely used metrics as well as four novel techniques proposed here. We begin by categorizing the methods according to which aspects of stereo computation they take into account and, then, assess their strengths and weaknesses. The evaluation is conducted on indoor and outdoor datasets with ground truth and measures the capability of each confidence metric to rank depth estimates according to their likelihood for being correct, to detect occluded pixels and to generate low-error depth maps by selecting among multiple hypotheses for each pixel. We believe that such an evaluation is missing from the rapidly maturing stereo literature and that our findings will be helpful to researchers in binocular and multi-view stereo.

Original languageEnglish
Title of host publication2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
Pages1466-1473
Number of pages8
DOIs
StatePublished - 2010
Event2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 - San Francisco, CA, United States
Duration: 13 Jun 201018 Jun 2010

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
Country/TerritoryUnited States
CitySan Francisco, CA
Period13/06/1018/06/10

Fingerprint

Dive into the research topics of 'Evaluation of stereo confidence indoors and outdoors'. Together they form a unique fingerprint.

Cite this