RT info:eu-repo/semantics/article T1 Calibration of a stereoscopic vision system in the presence of errors in pitch angle A1 Sigut Saavedra, Marta A1 Felipe, Jonatán A1 Acosta Sánchez, Leopoldo A2 Ingeniería Informática y de Sistemas K1 calibration K1 machine learning K1 U-V disparity K1 3D scenes reconstruction AB This paper proposes a novel method for the calibration of a stereo camera system usedto reconstruct 3D scenes. An error in the pitch angle of the cameras causes the reconstructed sceneto exhibit some distortion with respect to the real scene. To do the calibration procedure, whosepurpose is to eliminate or at least minimize said distortion, machine learning techniques have beenused, and more specifically, regression algorithms. These algorithms are trained with a large numberof vectors of input features with their respective outputs, since, in view of the application of theprocedure proposed, it is important that the training set be sufficiently representative of the varietythat can occur in a real scene, which includes the different orientations that the pitch angle can take,the error in said angle and the effect that all this has on the reconstruction process. The most efficientregression algorithms for estimating the error in the pitch angle are derived from decision trees andcertain neural network configurations. Once estimated, the error can be corrected, thus making thereconstructed scene appear more like the real one. Although the authors base their method on U-Vdisparity and employ this same technique to completely reconstruct the 3D scene, one of the mostinteresting features of the method proposed is that it can be applied regardless of the technique usedto carry out said reconstruction. YR 2022 FD 2022 LK http://riull.ull.es/xmlui/handle/915/34799 UL http://riull.ull.es/xmlui/handle/915/34799 LA en DS Repositorio institucional de la Universidad de La Laguna RD 08-oct-2024