{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T17:09:23Z","timestamp":1763226563033},"reference-count":35,"publisher":"Cambridge University Press (CUP)","issue":"10","license":[{"start":{"date-parts":[[2018,6,20]],"date-time":"2018-06-20T00:00:00Z","timestamp":1529452800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotica"],"published-print":{"date-parts":[[2018,10]]},"abstract":"<jats:title>SUMMARY<\/jats:title><jats:p>A robot should be able to estimate an accurate and dense 3D model of its environment (a map), along with its pose relative to it, all of it in real time, in order to be able to navigate autonomously without collisions.<\/jats:p><jats:p>As the robot moves from its starting position and the estimated map grows, the computational and memory footprint of a dense 3D map increases and might exceed the robot capabilities in a short time. However, a global map is still needed to maintain its consistency and plan for distant goals, possibly out of the robot field of view.<\/jats:p><jats:p>In this work, we address such problem by proposing a real-time stereo mapping pipeline, feasible for standard CPUs, which is locally dense and globally sparse and accurate. Our algorithm is based on a graph relating poses and salient visual points, in order to maintain a long-term accuracy with a small cost. Within such framework, we propose an efficient dense fusion of several stereo depths in the locality of the current robot pose.<\/jats:p><jats:p>We evaluate the performance and the accuracy of our algorithm in the public datasets of Tsukuba and KITTI, and demonstrate that it outperforms single-view stereo depth. We release the code as open-source, in order to facilitate the system use and comparisons.<\/jats:p>","DOI":"10.1017\/s0263574718000528","type":"journal-article","created":{"date-parts":[[2018,6,20]],"date-time":"2018-06-20T07:55:41Z","timestamp":1529481341000},"page":"1510-1526","source":"Crossref","is-referenced-by-count":12,"title":["Real-time dense map fusion for stereo SLAM"],"prefix":"10.1017","volume":"36","author":[{"given":"Taih\u00fa","family":"Pire","sequence":"first","affiliation":[]},{"given":"Rodrigo","family":"Baravalle","sequence":"additional","affiliation":[]},{"given":"Ariel","family":"D'Alessandro","sequence":"additional","affiliation":[]},{"given":"Javier","family":"Civera","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2018,6,20]]},"reference":[{"key":"S0263574718000528_ref30","first-page":"11","volume-title":"Real-Time Dense Geometry from a Handheld Camera","author":"St\u00fchmer","year":"2010"},{"key":"S0263574718000528_ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"#cr-split#-S0263574718000528_ref17.1","doi-asserted-by":"crossref","unstructured":"1. G. Kuschk, A. Bo??i?? and D. Cremers, \"Real-Time Variational Stereo Reconstruction with Applications to Large-Scale Dense SLAM,\" Proceedings of the 2017 IEEE Intelligent Vehicles Symposium","DOI":"10.1109\/IVS.2017.7995899"},{"key":"#cr-split#-S0263574718000528_ref17.2","unstructured":"2. (IV) (Jun. 2017) pp. 1348-1355."},{"key":"S0263574718000528_ref16","doi-asserted-by":"crossref","unstructured":"M. Klingensmith , I. Dryanovski , S. Srinivasa and J. Xiao , \u201cChisel: Real Time Large Scale 3D Reconstruction Onboard a Mobile Device using Spatially Hashed Signed Distance Fields,\u201d Proceedings of Robotics: Science and Systems, volume 4, Rome, Italy (Jul. 2015).","DOI":"10.15607\/RSS.2015.XI.040"},{"key":"S0263574718000528_ref19","doi-asserted-by":"crossref","unstructured":"W. Maddern and P. Newman , \u201cReal-Time Probabilistic Fusion of Sparse 3D LIDAR and Dense Stereo,\u201d Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE (2016) pp. 2181\u20132188.","DOI":"10.1109\/IROS.2016.7759342"},{"key":"S0263574718000528_ref3","doi-asserted-by":"crossref","unstructured":"S. Y. Bao , M. Chandraker , Y. Lin and S. Savarese , \u201cDense Object Reconstruction with Semantic Priors,\u201d Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition CVPR2013, Washington, DC, USA, IEEE Computer Society (2013) pp. 1264\u20131271.","DOI":"10.1109\/CVPR.2013.167"},{"key":"S0263574718000528_ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.421"},{"key":"S0263574718000528_ref24","unstructured":"M. Peris , S. Martull , A. Maki , Y. Ohkawa and K. Fukui , \u201cTowards a Simulation Driven Stereo Vision System,\u201d Proceedings of the 21st International Conference on Pattern Recognition ICPR2012 (Nov. 2012) pp. 1038\u20131042."},{"key":"S0263574718000528_ref15","doi-asserted-by":"crossref","unstructured":"G. Graber , T. Pock and H. Bischof , \u201cOnline 3D Reconstruction using Convex Optimization,\u201d Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCV Workshops) (Nov. 2011) pp. 708\u2013711.","DOI":"10.1109\/ICCVW.2011.6130318"},{"key":"S0263574718000528_ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.09.007"},{"key":"S0263574718000528_ref11","unstructured":"J. Engel , J. St\u00fcckler and D. Cremers , \u201cLarge-Scale Direct Slam with Stereo Cameras,\u201d Proceedings of the IEEE International Conference on Intelligent Robots and Systems IROS2015, IEEE (2015) pp. 1935\u20131942."},{"key":"S0263574718000528_ref22","doi-asserted-by":"crossref","unstructured":"R. A. Newcombe , S. J. Lovegrove and A. J. Davison , \u201cDTAM: Dense Tracking and Mapping in Real-time,\u201d Proceedings of the IEEE International Conference on Computer Vision ICCV2011, Washington, DC, USA, IEEE Computer Society (2011) pp. 2320\u20132327.","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"S0263574718000528_ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0489-0"},{"key":"S0263574718000528_ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1678144"},{"key":"S0263574718000528_ref14","first-page":"25","volume-title":"Efficient Large-Scale Stereo Matching","author":"Geiger","year":"2011"},{"key":"S0263574718000528_ref29","doi-asserted-by":"crossref","unstructured":"S. Sengupta , E. Greveson , A. Shahrokni and P. Torr , \u201cUrban 3D Semantic Modelling Using Stereo Vision,\u201d Proceedings of the IEEE International Conference on Robotics and Automation (May 2013) pp. 580\u2013585.","DOI":"10.1109\/ICRA.2013.6630632"},{"key":"S0263574718000528_ref26","doi-asserted-by":"crossref","unstructured":"T. Pire , T. Fischer , J. Civera , P. De~Crist\u00f3foris and J. J. Berlles , \u201cStereo Parallel Tracking and Mapping for Robot Localization,\u201d Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems IROS2015 (Sep. 2015) pp. 1373\u20131378.","DOI":"10.1109\/IROS.2015.7353546"},{"key":"S0263574718000528_ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"S0263574718000528_ref10","doi-asserted-by":"crossref","unstructured":"J. Engel , V. Koltun and D. Cremers , \u201cDirect sparse odometry,\u201d IEEE Trans. Pattern Anal. Mach. Intell. (2017).","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"S0263574718000528_ref7","doi-asserted-by":"crossref","unstructured":"A. Concha , G. Loianno , V. Kumar and J. Civera , \u201cVisual-Inertial Direct SLAM,\u201d Proceedings of the IEEE International Conference on Robotics and Automation ICRA2016 (May 2016) pp. 1331\u20131338.","DOI":"10.1109\/ICRA.2016.7487266"},{"key":"S0263574718000528_ref33","doi-asserted-by":"crossref","unstructured":"V. Vineet , O. Miksik , M. Lidegaard , M. Nie\u00dfner , S. Golodetz , V. A. Prisacariu , O. K\u00e4hler , D. W. Murray , S. Izadi , P. P\u00e9rez and P. H. S. Torr , \u201cIncremental Dense Semantic Stereo Fusion for Large-Scale Semantic Scene Reconstruction,\u201d Proceedings of the 2015 IEEE International Conference on Robotics and Automation ICRA2015 (May 2015) pp. 75\u201382.","DOI":"10.1109\/ICRA.2015.7138983"},{"key":"S0263574718000528_ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"key":"S0263574718000528_ref27","doi-asserted-by":"crossref","unstructured":"M. Pizzoli , C. Forster and D. Scaramuzza , \u201cREMODE: Probabilistic, Monocular Dense Reconstruction in Real Time,\u201d Proceedings of the IEEE International Conference on Robotics and Automation ICRA2014, IEEE (2014) pp. 2609\u20132616.","DOI":"10.1109\/ICRA.2014.6907233"},{"key":"S0263574718000528_ref12","doi-asserted-by":"crossref","unstructured":"A. Geiger , J. Ziegler and C. Stiller , \u201cStereoScan: Dense 3D Reconstruction in Real-Time,\u201d Proceedings of the IEEE Intelligent Vehicles Symposium (IV) (Jun. 2011) pp. 963\u2013968.","DOI":"10.1109\/IVS.2011.5940405"},{"key":"S0263574718000528_ref6","doi-asserted-by":"crossref","unstructured":"A. Concha , W. Hussain , L. Montano and J. Civera , \u201cManhattan and Piecewise-Planar Constraints for Dense Monocular Mapping,\u201d Proceedings of Robotics: Science and Systems, Berkeley, USA (Jul. 2014).","DOI":"10.15607\/RSS.2014.X.016"},{"key":"S0263574718000528_ref31","unstructured":"M. Tanner , P. Pinies , L. M. Paz and P. Newman , \u201cDENSER cities: A system for dense efficient reconstructions of cities,\u201d arXiv:1604.03734, 2016."},{"key":"S0263574718000528_ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.03.019"},{"key":"S0263574718000528_ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1049"},{"key":"S0263574718000528_ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"S0263574718000528_ref23","doi-asserted-by":"crossref","unstructured":"H. Oleynikova , Z. Taylor , M. Fehr , R. Siegwart and J. Nieto , \u201cVoxblox: Incremental 3D Euclidean Signed Distance Fields for on-board MAV planning,\u201d Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems IROS2017 (Sep. 2017) pp. 1366\u20131373.","DOI":"10.1109\/IROS.2017.8202315"},{"key":"S0263574718000528_ref1","unstructured":"P. Alcantarilla , C. Beall and F. Dellaert , \u201cLarge-Scale dense 3D Reconstruction from Stereo Imagery,\u201d Proceedings of the 5th Workshop on Planning, Perception and Navigation for Intelligent Vehicles PPNV2013. Georgia Institute of Technology (Nov. 2013)."},{"key":"S0263574718000528_ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-012-0313-2"},{"key":"S0263574718000528_ref5","doi-asserted-by":"crossref","unstructured":"D. M. Cole and P. M. Newman , \u201cUsing Laser Range Data for 3D SLAM in Outdoor Environments,\u201d Proceedings of the IEEE International Conference on Robotics and Automation ICRA2006 (May 2006) pp. 1556\u20131563.","DOI":"10.1109\/ROBOT.2006.1641929"},{"key":"S0263574718000528_ref20","doi-asserted-by":"crossref","unstructured":"O. Miksik , Y. Amar , V. Vineet , P. Prez and P. Torr , \u201cIncremental Dense Multi-Modal 3D Scene Reconstruction,\u201d Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (Sep. 2015) pp. 908\u2013915.","DOI":"10.1109\/IROS.2015.7353479"}],"container-title":["Robotica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0263574718000528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,19]],"date-time":"2019-10-19T18:31:19Z","timestamp":1571509879000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0263574718000528\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,20]]},"references-count":35,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2018,10]]}},"alternative-id":["S0263574718000528"],"URL":"https:\/\/doi.org\/10.1017\/s0263574718000528","relation":{},"ISSN":["0263-5747","1469-8668"],"issn-type":[{"value":"0263-5747","type":"print"},{"value":"1469-8668","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,20]]}}}