000061824 001__ 61824 000061824 005__ 20200221144301.0 000061824 0247_ $$2doi$$a10.1016/j.robot.2015.08.009 000061824 0248_ $$2sideral$$a100379 000061824 037__ $$aART-2016-100379 000061824 041__ $$aeng 000061824 100__ $$0(orcid)0000-0003-0225-7689$$aGálvel-López, Dorian 000061824 245__ $$aReal-time monocular object SLAM 000061824 260__ $$c2016 000061824 5060_ $$aAccess copy available to the general public$$fUnrestricted 000061824 5203_ $$aWe present a real-time object-based SLAM system that leverages the largest object database to date. Our approach comprises two main components: 1) a monocular SLAM algorithm that exploits object rigidity constraints to improve the map and find its real scale, and 2) a novel object recognition algorithm based on bags of binary words, which provides live detections with a database of 500 3D objects. The two components work together and benefit each other: the SLAM algorithm accumulates information from the observations of the objects, anchors object features to especial map landmarks and sets constrains on the optimization. At the same time, objects partially or fully located within the map are used as a prior to guide the recognition algorithm, achieving higher recall. We evaluate our proposal on five real environments showing improvements on the accuracy of the map and eficiency with respect to other state-of-the-art techniques. 000061824 536__ $$9info:eu-repo/grantAgreement/ES/MINECO/DPI2012-36070$$9info:eu-repo/grantAgreement/ES/MINECO/DPI2012-32168$$9info:eu-repo/grantAgreement/EC/FP7/248942/EU/RoboEarth: robots sharing a knowledge base for world modelling and learning of actions/RoboEarth$$9info:eu-repo/grantAgreement/ES/DGA/T04 000061824 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/ 000061824 590__ $$a1.95$$b2016 000061824 591__ $$aAUTOMATION & CONTROL SYSTEMS$$b28 / 60 = 0.467$$c2016$$dQ2$$eT2 000061824 591__ $$aROBOTICS$$b14 / 26 = 0.538$$c2016$$dQ3$$eT2 000061824 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b60 / 133 = 0.451$$c2016$$dQ2$$eT2 000061824 592__ $$a0.928$$b2016 000061824 593__ $$aComputer Science Applications$$c2016$$dQ1 000061824 593__ $$aSoftware$$c2016$$dQ1 000061824 593__ $$aMathematics (miscellaneous)$$c2016$$dQ1 000061824 593__ $$aControl and Systems Engineering$$c2016$$dQ1 000061824 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/submittedVersion 000061824 700__ $$0(orcid)0000-0001-8026-4388$$aSalas, Marta 000061824 700__ $$0(orcid)0000-0002-4518-5876$$aTardos Solano, Juan Domingo$$uUniversidad de Zaragoza 000061824 700__ $$0(orcid)0000-0002-3627-7306$$aMartínez Montiel, José María$$uUniversidad de Zaragoza 000061824 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát. 000061824 773__ $$g75, Part B (2016), 435-449$$pRobot. auton. syst.$$tROBOTICS AND AUTONOMOUS SYSTEMS$$x0921-8890 000061824 8564_ $$s6565505$$uhttps://zaguan.unizar.es/record/61824/files/texto_completo.pdf$$yPreprint 000061824 8564_ $$s8683$$uhttps://zaguan.unizar.es/record/61824/files/texto_completo.jpg?subformat=icon$$xicon$$yPreprint 000061824 909CO $$ooai:zaguan.unizar.es:61824$$particulos$$pdriver 000061824 951__ $$a2020-02-21-13:32:31 000061824 980__ $$aARTICLE