60652 20200221144300.0 doi 10.3390/robotics5040025 sideral 98049 ART-2016-98049 eng Gonzalez, Ramon Improving Robot Mobility by Combining Downward-Looking and Frontal Cameras 2016 Access copy available to the general public Unrestricted This paper presents a novel attempt to combine a downward-looking camera and a forward-looking camera for terrain classification in the field of off-road mobile robots. The first camera is employed to identify the terrain beneath the robot. This information is then used to improve the classification of the forthcoming terrain acquired from the frontal camera. This research also shows the usefulness of the Gist descriptor for terrain classification purposes. Physical experiments conducted in different terrains (quasi-planar terrains) and different lighting conditions, confirm the satisfactory performance of this approach in comparison with a simple color-based classifier based only on frontal images. Our proposal substantially reduces the misclassification rate of the color-based classifier (~10% versus ~20%). info:eu-repo/grantAgreement/ES/MINECO/DPI2015-65962-R info:eu-repo/semantics/openAccess by http://creativecommons.org/licenses/by/3.0/es/ 0.0 2016 Artificial Intelligence 2016 Mechanical Engineering 2016 Control and Optimization 2016 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion (orcid)0000-0001-6738-3382 Rituerto, Alejandro (orcid)0000-0001-5209-2267 Guerrero, J.J. Universidad de Zaragoza 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 5, 4 (2016), [19 pp.] Robotics 2218-6581 7200352 http://zaguan.unizar.es/record/60652/files/texto_completo.pdf Versión publicada 106983 http://zaguan.unizar.es/record/60652/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:60652 articulos driver 2020-02-21-13:32:02 ARTICLE