A robustness study of a CNN based stereo vision algorithm

The development of an effective system for autonomous robot navigation can find a valid support from the CNN approach. In the paper some measurements of the robustness of a stereo vision algorithm based on the CNN paradigm are presented. The sensitivity of the algorithm to the difference in luminosity and contrast of the images in the stereo pair, the presence of noise corrupting the images and problems of misalignment in the experimental set-up are investigated