doi:10.1109/LRA.2018.2860039engBescós, BertaFácil, José MaríaCivera, JavierNeira, JoséDynaSLAM: Tracking, Mapping and Inpainting in Dynamic ScenesART-2018-106907The assumption of scene rigidity is typical in SLAM algorithms. Such a strong assumption limits the use of most visual SLAM systems in populated real-world environments, which are the target of several relevant applications like service robotics or autonomous vehicles. In this paper we present DynaSLAM, a visual SLAM system that, building on ORB- SLAM2 [1], adds the capabilities of dynamic object detection and background inpainting. DynaSLAM is robust in dynamic scenarios for monocular, stereo and RGB-D configurations. We are capable of detecting the moving objects either by multi-view geometry, deep learning or both. Having a static map of the scene allows inpainting the frame background that has been occluded by such dynamic objects. We evaluate our system in public monocular, stereo and RGB-D datasets. We study the impact of several accuracy/speed trade-offs to assess the limits of the proposed methodology. DynaSLAM outperforms the accuracy of standard visual SLAM baselines in highly dynamic scenarios. And it also estimates a map of the static parts of the scene, which is a must for long-term applications in real-world environments2018http://zaguan.unizar.es/record/7118310.1109/LRA.2018.2860039http://zaguan.unizar.es/record/71183oai:zaguan.unizar.es:71183info:eu-repo/grantAgreement/ES/DGA/T04info:eu-repo/grantAgreement/ES/MINECO/BES-2016-077836info:eu-repo/grantAgreement/ES/MINECO/DPI2015-67275info:eu-repo/grantAgreement/ES/MINECO/DPI2015-68905-PIEEE ROBOTICS AND AUTOMATION LETTERS 3, 4 (2018), 4076 - 4083byhttp://creativecommons.org/licenses/by/3.0/es/info:eu-repo/semantics/openAccess