Stereo matching with VG-RAM Weightless Neural Networks

Abstract

Virtual Generalizing Random Access Memory Weightless Neural Networks (VG-RAM WNN) is an effective machine learning technique that offers simple implementation and fast training and test. We examined the performance of VG-RAM WNN on binocular dense stereo matching using the Middlebury Stereo Datasets. Our experimental results showed that, even without tackling occlusions and discontinuities in the stereo image pairs examined, our VG-RAM WNN architecture for stereo matching was able to rank at 114th position in the Middlebury Stereo Evaluation system. This result is promising, because the difference in performance among approaches ranked in distinct positions is very small.

DOI: 10.1109/ISDA.2012.6416556

12 Figures and Tables

Cite this paper

@article{Veronese2012StereoMW, title={Stereo matching with VG-RAM Weightless Neural Networks}, author={Lucas de Paula Veronese and Lauro Jose Lyrio Junior and Filipe Wall Mutz and Jorcy de Oliveira Neto and Vitor Barbirato}, journal={2012 12th International Conference on Intelligent Systems Design and Applications (ISDA)}, year={2012}, pages={309-314} }