36752 20210121114453.0 doi 10.1109/IROS.2015.7354184 sideral 92153 ART-2015-92153 eng (orcid)0000-0001-6418-3828 Concha Belenguer, Alejo DPPTAM: Dense Piecewise Planar Tracking and Mapping from a Monocular Sequence 2015 Access copy available to the general public Unrestricted This paper proposes a direct monocular SLAM algorithm that estimates a dense reconstruction of a scene in real-time on a CPU. Highly textured image areas are mapped using standard direct mapping techniques [1], that minimize the photometric error across different views. We make the assumption that homogeneous-color regions belong to approximately planar areas. Our contribution is a new algorithm for the estimation of such planar areas, based on the information of a superpixel segmentation and the semidense map from highly textured areas. We compare our approach against several alternatives using the public TUM dataset [2] and additional live experiments with a hand-held camera. We demonstrate that our proposal for piecewise planar monocular SLAM is faster, more accurate and more robust than the piecewise planar baseline [3]. In addition, our experimental results show how the depth regularization of monocular maps can damage its accuracy, being the piecewise planar assumption a reasonable option in indoor scenarios. info:eu-repo/grantAgreement/ES/MINECO/DPI2012-32168 info:eu-repo/grantAgreement/ES/MINECO/IPT2012-1309-430000 info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ 0.843 2015 Computer Science Applications 2015 Software 2015 Control and Systems Engineering 2015 Computer Vision and Pattern Recognition 2015 info:eu-repo/semantics/article info:eu-repo/semantics/submittedVersion (orcid)0000-0003-1368-1151 Civera Sancho, Javier Universidad de Zaragoza 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 2015 (2015), [8 pp.] Proc. IEEE/RSJ Int. Conf. Intell. Rob. Syst. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems 2153-0858 2378528 http://zaguan.unizar.es/record/36752/files/texto_completo.pdf Preprint 111800 http://zaguan.unizar.es/record/36752/files/texto_completo.jpg?subformat=icon icon Preprint oai:zaguan.unizar.es:36752 articulos driver 2021-01-21-10:47:00 ARTICLE