Abstract
With the aim to improve accuracy of stereo confifidence measures, we apply the random decision forest framework to a large set of diverse stereo confifidence 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 dataterm, which is the best performing realtime capable stereo method known to date. On KITTI images, SGM still produces a signifificant amount of error. We obtain consistently improved area under curve values of sparsifification measures in comparison to best performing single stereo confifidence measures where numbers of stereo errors are large. More specififically, our method performs best in all but one out of 194 frames of the KITTI dataset.