Ensemble Learning for Confidence Measures in Stereo Vision

With the aim to improve accuracy of stereo confidence measures, we apply the random decision forest framework to a large set of diverse stereo confidence measures. Learning and testing sets were drawn from the recently introduced KITTI dataset, which currently poses higher challenges to stereo solve...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 305 - 312
Main Authors Haeusler, Ralf, Nair, Rahul, Kondermann, Daniel
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2013
Subjects
Accuracy
benchmarking
confidence measure
Feature extraction
Measurement uncertainty
random forest
Reliability
stereo
Stereo vision
Vectors
Vegetation
Online AccessGet full text

Cover

More Information
Summary:With the aim to improve accuracy of stereo confidence measures, we apply the random decision forest framework to a large set of diverse stereo confidence measures. Learning and testing sets were drawn from the recently introduced KITTI dataset, which currently poses higher challenges to stereo solvers than other benchmarks with ground truth for stereo evaluation. We experiment with semi global matching stereo (SGM) and a census data term, which is the best performing real-time capable stereo method known to date. On KITTI images, SGM still produces a significant amount of error. We obtain consistently improved area under curve values of sparsification measures in comparison to best performing single stereo confidence measures where numbers of stereo errors are large. More specifically, our method performs best in all but one out of 194 frames of the KITTI dataset.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2013.46