Exploiting the Power of Stereo Confidences

Ensemble Learning for Confidence Measures in Stereo Vision

“…Applications where accurate stereo confidence measures are essential in raising reliability of computer vision include sparse [19] or dense [16] 3D scene reconstructions.…”

Priors for Stereo Vision under Adverse Weather Conditions

“…The Heidelberg HCI dataset 1 was the first data set covering challeng-1 http://hci.iwr.uni-heidelberg.de/Benchmarks ing weather scenarios, however, without supplying ground truth. The Ground Truth Stixel Dataset [23] contains a set of rainy highway scenes with sparse ground truth labels for the free space. For driver assistance, the immediate surroundings of the car that limit the free space should be detected at all times but without mistakenly detecting a structure within the free space.…”

Extending the Stixel World with online self-supervised color modeling for road-versus-obstacle segmentation

“…This is beneficiary for the baseline Stixel World method, since it can handle missing values better than erroneous ones. This can be seen as a simplification of the work presented in [19], in which disparity estimates are accompanied by a confidence measure to adaptively set a outlier probability. In our approach, this confidence is binary with a relatively strict threshold based on the winner margin.…”