000128134 001__ 128134 000128134 005__ 20241125101145.0 000128134 0247_ $$2doi$$a10.1109/LRA.2023.3251722 000128134 0248_ $$2sideral$$a135269 000128134 037__ $$aART-2023-135269 000128134 041__ $$aeng 000128134 100__ $$aFontan, Alejandro 000128134 245__ $$aSID-SLAM: Semi-Direct Information-Driven RGB-D SLAM 000128134 260__ $$c2023 000128134 5060_ $$aAccess copy available to the general public$$fUnrestricted 000128134 5203_ $$aThis work presents SID-SLAM, a complete SLAM framework for RGB-D cameras. Our main contribution is a semi-direct approach that, for the first time, combines tightly and indistinctly photometric and feature-based image measurements. Additionally, SID-SLAM uses information metrics to reduce the state size with a minimal impact in the accuracy. Our evaluation on several public datasets shows that we achieve state-of-the-art performance regarding accuracy, robustness and computational footprint in CPU real time. In order to facilitate research on semi-direct SLAM, we record the Minimal Texture dataset, composed by RGB-D sequences challenging for current baselines and in which our pipeline excels. 000128134 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T45-20R$$9info:eu-repo/grantAgreement/ES/MICINN/PID2021-127685NB-I00$$9info:eu-repo/grantAgreement/EUR/MICINN/TED2021-131150B-I00 000128134 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/ 000128134 590__ $$a4.6$$b2023 000128134 592__ $$a2.119$$b2023 000128134 591__ $$aROBOTICS$$b12 / 46 = 0.261$$c2023$$dQ2$$eT1 000128134 593__ $$aArtificial Intelligence$$c2023$$dQ1 000128134 593__ $$aBiomedical Engineering$$c2023$$dQ1 000128134 593__ $$aComputer Science Applications$$c2023$$dQ1 000128134 593__ $$aMechanical Engineering$$c2023$$dQ1 000128134 593__ $$aControl and Optimization$$c2023$$dQ1 000128134 593__ $$aControl and Systems Engineering$$c2023$$dQ1 000128134 593__ $$aHuman-Computer Interaction$$c2023$$dQ1 000128134 593__ $$aComputer Vision and Pattern Recognition$$c2023$$dQ1 000128134 594__ $$a9.6$$b2023 000128134 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion 000128134 700__ $$aGiubilato, Riccardo 000128134 700__ $$aMaza, Laura Oliva 000128134 700__ $$0(orcid)0000-0003-1368-1151$$aCivera, Javier$$uUniversidad de Zaragoza 000128134 700__ $$aTriebel, Rudolph 000128134 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát. 000128134 773__ $$g8, 10 (2023), 6387-6394$$pIEEE Robot. autom. let.$$tIEEE Robotics and Automation Letters$$x2377-3766 000128134 8564_ $$s8800097$$uhttps://zaguan.unizar.es/record/128134/files/texto_completo.pdf$$yPostprint 000128134 8564_ $$s3213446$$uhttps://zaguan.unizar.es/record/128134/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint 000128134 909CO $$ooai:zaguan.unizar.es:128134$$particulos$$pdriver 000128134 951__ $$a2024-11-22-12:04:12 000128134 980__ $$aARTICLE