{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:45:26Z","timestamp":1762368326495,"version":"build-2065373602"},"reference-count":50,"publisher":"Tsinghua University Press","issue":"1","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,1,7]],"date-time":"2021-01-07T00:00:00Z","timestamp":1609977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s41095-020-0195-3","type":"journal-article","created":{"date-parts":[[2021,1,7]],"date-time":"2021-01-07T06:04:21Z","timestamp":1609999461000},"page":"87-101","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["ClusterSLAM: A SLAM backend for simultaneous rigid body clustering and motion estimation"],"prefix":"10.26599","volume":"7","author":[{"given":"Jiahui","family":"Huang","sequence":"first","affiliation":[{"name":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba A.I. Labs, Hangzhou 311121, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zishuo","family":"Zhao","sequence":"additional","affiliation":[{"name":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, CF24 3AA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shi-Min","family":"Hu","sequence":"additional","affiliation":[{"name":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"11138","reference":[{"key":"195_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, P.; Tipaldi, G. D.; Spinello, L.; Stachniss, C.; Burgard, W. Robust map optimization using dynamic covariance scaling. In: Proceedings of the IEEE International Conference on Robotics and Automation, 62\u201369, 2013.","DOI":"10.1109\/ICRA.2013.6630557"},{"key":"195_CR2","unstructured":"Carlone, L.; Censi, A.; Dellaert, F. Selecting good measurements via \u21131 relaxation: A convex approach for robust estimation over graphs. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, 2667\u20132674, 2014."},{"issue":"6","key":"195_CR3","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1109\/TRO.2016.2609395","volume":"32","author":"D H Kim","year":"2016","unstructured":"Kim, D. H.; Kim, J. H. Effective background model-based RGB-D dense visual odometry in a dynamic environment. IEEE Transactions on Robotics Vol. 32, No. 6, 1565\u20131573, 2016.","journal-title":"IEEE Transactions on Robotics"},{"issue":"4","key":"195_CR4","doi-asserted-by":"publisher","first-page":"4076","DOI":"10.1109\/LRA.2018.2860039","volume":"3","author":"B Bescos","year":"2018","unstructured":"Bescos, B.; Facil, J. M.; Civera, J.; Neira, J. DynaSLAM: Tracking, mapping, and inpainting in dynamic scenes. IEEE Robotics and Automation Letters Vol. 3, No. 4, 4076\u20134083, 2018.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"195_CR5","unstructured":"R\u00fcnz, M.; Agapito, L. Co-fusion: Real-time segmentation, tracking and fusion of multiple objects. In: Proceedings of the IEEE International Conference on Robotics and Automation, 4471\u20134478, 2017."},{"key":"195_CR6","unstructured":"Runz, M.; Buffier, M.; Agapito, L. MaskFusion: Real-time recognition, tracking and reconstruction of multiple moving objects. In: Proceedings of the IEEE International Symposium on Mixed and Augmented Reality, 10\u201320, 2018."},{"key":"195_CR7","doi-asserted-by":"crossref","unstructured":"Barsan, I. A.; Liu, P.; Pollefeys, M.; Geiger, A. Robust dense mapping for large-scale dynamic environments. In: Proceedings of the IEEE International Conference on Robotics and Automation, 7510\u20137517, 2018.","DOI":"10.1109\/ICRA.2018.8462974"},{"key":"195_CR8","unstructured":"Xu, B.; Li, W.; Tzoumanikas, D.; Bloesch, M.; Davison, A.; Leutenegger, S.; MID-fusion: Octree-based object-level multi-instance dynamic SLAM. In: Proceedings of the IEEE International Conference on Robotics and Automation, 5231\u20135237, 2019."},{"key":"195_CR9","doi-asserted-by":"crossref","unstructured":"Paull, L.; Huang, G.; Seto, M.; Leonard, J. J. Communication-constrained multi-AUV cooperative SLAM. In: Proceedings of the IEEE International Conference on Robotics and Automation, 509\u2013516, 2015.","DOI":"10.1109\/ICRA.2015.7139227"},{"key":"195_CR10","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/978-3-030-01216-8_40","volume-title":"Computer Vision \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11206","author":"P L Li","year":"2018","unstructured":"Li, P. L.; Qin, T.; Shen, S. J. Stereo vision-based semantic 3D object and ego-motion tracking for autonomous driving. In: Computer Vision \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11206. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 664\u2013679, 2018."},{"key":"195_CR11","doi-asserted-by":"crossref","unstructured":"Jaimez, M.; Kerl, C.; Gonzalez-Jimenez, J.; Cremers, D. Fast odometry and scene flow from RGB-D cameras based on geometric clustering. In: Proceedings of the IEEE International Conference on Robotics and Automation, 3992\u20133999, 2017.","DOI":"10.1109\/ICRA.2017.7989459"},{"key":"195_CR12","doi-asserted-by":"crossref","unstructured":"He, K.; Gkioxari, G.; Doll\u00e1r, P.; Girshick, R. Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, 2961\u20132969, 2017.","DOI":"10.1109\/ICCV.2017.322"},{"issue":"4","key":"195_CR13","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L C Chen","year":"2018","unstructured":"Chen, L. C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A. L. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 40, No. 4, 834\u2013848, 2018.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"195_CR14","doi-asserted-by":"crossref","unstructured":"Lenz, P.; Ziegler, J.; Geiger, A.; Roser, M. Sparse scene flow segmentation for moving object detection in urban environments. In: Proceedings of the IEEE Intelligent Vehicles Symposium, 926\u2013932, 2011.","DOI":"10.1109\/IVS.2011.5940558"},{"key":"195_CR15","unstructured":"Huang, J.; Yang, S.; Zhao, Z.; Lai, Y.-K.; Hu, S.-M. Clusterslam: A slam backend for simultaneous rigid body clustering and motion estimation. In: Proceedings of the IEEE International Conference on Computer Vision, 5875\u20135884, 2019."},{"issue":"11","key":"195_CR16","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A.; Lenz, P.; Stiller, C.; Urtasun, R. Vision meets robotics: The KITTI dataset. The International Journal of Robotics Research Vol. 32, No. 11, 1231\u20131237, 2013.","journal-title":"The International Journal of Robotics Research"},{"key":"195_CR17","doi-asserted-by":"crossref","unstructured":"Alcantarilla, P. F.; Yebes, J. J.; Almaz\u00e1n, J.; Bergasa, L. M. On combining visual SLAM and dense scene flow to increase the robustness of localization and mapping in dynamic environments. In: Proceedings of the IEEE International Conference on Robotics and Automation, 1290\u20131297, 2012.","DOI":"10.1109\/ICRA.2012.6224690"},{"issue":"5","key":"195_CR18","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","volume":"33","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal, R.; Tardos, J. D. ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE Transactions on Robotics Vol. 33, No. 5, 1255\u20131262, 2017.","journal-title":"IEEE Transactions on Robotics"},{"key":"195_CR19","doi-asserted-by":"crossref","unstructured":"Kundu, A.; Krishna, K. M.; Jawahar, C. Realtime multibody visual SLAM with a smoothly moving monocular camera. In: Proceedings of the IEEE International Conference on Computer Vision, 2080\u20132087, 2011.","DOI":"10.1109\/ICCV.2011.6126482"},{"key":"195_CR20","unstructured":"Judd, K. M.; Gammell, J. D.; Newman, P. Multimotion visual odometry (MVO): Simultaneous estimation of camera and third-party motions. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, 3949\u20133956, 2018."},{"key":"195_CR21","unstructured":"Dinesh Reddy, N.; Vo, M.; Narasimhan, S. G. CarFusion: Combining point tracking and part detection for dynamic 3D reconstruction of vehicles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1906\u20131915, 2018."},{"key":"195_CR22","unstructured":"Strecke, M.; Stuckler, J. Em-fusion: Dynamic object-level slam with probabilistic data association. In: Proceedings of the IEEE International Conference on Computer Vision, 5865\u20135874, 2019."},{"issue":"2","key":"195_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3177853","volume":"51","author":"M R U Saputra","year":"2018","unstructured":"Saputra, M. R. U.; Markham, A.; Trigoni, N. Visual SLAM and structure from motion in dynamic environments. ACM Computing Surveys Vol. 51, No. 2, 1\u201336, 2018.","journal-title":"ACM Computing Surveys"},{"issue":"3","key":"195_CR24","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1023\/A:1008000628999","volume":"29","author":"J P Costeira","year":"1998","unstructured":"Costeira, J. P.; Kanade, T. A multibody factorization method for independently moving objects. International Journal of Computer Vision Vol. 29, No. 3, 159\u2013179, 1998.","journal-title":"International Journal of Computer Vision"},{"key":"195_CR25","doi-asserted-by":"crossref","unstructured":"Li, T.; Kallem, V.; Singaraju, D.; Vidal, R. Projective factorization of multiple rigid-body motions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1\u20136, 2007.","DOI":"10.1109\/CVPR.2007.383090"},{"issue":"6","key":"195_CR26","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"M A Fischler","year":"1981","unstructured":"Fischler, M. A.; Bolles, R. C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM Vol. 24, No. 6, 381\u2013395, 1981.","journal-title":"Communications of the ACM"},{"key":"195_CR27","doi-asserted-by":"crossref","unstructured":"Azartash, H.; Lee, K.; Nguyen, T. Q. Visual odometry for RGB-D cameras for dynamic scenes. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 1280\u20131284, 2014.","DOI":"10.1109\/ICASSP.2014.6853803"},{"key":"195_CR28","doi-asserted-by":"crossref","unstructured":"Xu, X.; Cheong, L.F.; Li, Z. Motion segmentation by exploiting complementary geometric models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2859\u20132867, 2018.","DOI":"10.1109\/CVPR.2018.00302"},{"issue":"1","key":"195_CR29","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s11263-005-4839-7","volume":"68","author":"R Vidal","year":"2006","unstructured":"Vidal, R.; Ma, Y.; Soatto, S.; Sastry, S. Two-view multibody structure from motion. International Journal of Computer Vision Vol. 68, No. 1, 7\u201325, 2006.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"195_CR30","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1109\/TPAMI.2007.1179","volume":"30","author":"R Vidal","year":"2008","unstructured":"Vidal, R.; Hartley, R. Three-view multibody structure from motion. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 30, No. 2, 214\u2013227, 2008.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"195_CR31","unstructured":"Ilg, E.; Mayer, N.; Saikia, T.; Keuper, M.; Dosovitskiy, A.; Brox, T. FlowNet 2.0: Evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE International Conference on Computer Vision, 2462\u20132470, 2017."},{"issue":"3","key":"195_CR32","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/s11390-018-1833-4","volume":"33","author":"Z-F Xie","year":"2018","unstructured":"Xie, Z.-F.; Guo, Y.-C.; Zhang, S.-H.; Zhang, W.-J.; Ma, L.-Z. Multi-exposure motion estimation based on deep convolutional networks. Journal of Computer Science and Technology Vol. 33, No. 3, 487\u2013501, 2018.","journal-title":"Journal of Computer Science and Technology"},{"issue":"3","key":"195_CR33","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1007\/s11390-017-1741-z","volume":"32","author":"C C Zhang","year":"2017","unstructured":"Zhang, C. C.; Liu, Z. L. Prior-free dependent motion segmentation using Helmholtz-Hodge decomposition based object-motion oriented map. Journal of Computer Science and Technology Vol. 32, No. 3, 520\u2013535, 2017.","journal-title":"Journal of Computer Science and Technology"},{"issue":"2","key":"195_CR34","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s11263-011-0474-7","volume":"97","author":"H Isack","year":"2012","unstructured":"Isack, H.; Boykov, Y. Energy-based geometric multimodel fitting. International Journal of Computer Vision Vol. 97, No. 2, 123\u2013147, 2012.","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"195_CR35","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s41095-017-0083-7","volume":"3","author":"R C Fan","year":"2017","unstructured":"Fan, R. C.; Zhang, F. L., Zhang, M.; Martin, R. R. Robust tracking-by-detection using a selection and completion mechanism. Computational Visual Media Vol. 3, No. 3, 285\u2013294, 2017.","journal-title":"Computational Visual Media"},{"issue":"1","key":"195_CR36","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s10462-016-9477-7","volume":"47","author":"G Yuan","year":"2017","unstructured":"Yuan, G.; Sun, P. H.; Zhao, J.; Li, D. X.; Wang, C. W. A review of moving object trajectory clustering algorithms. Artificial Intelligence Review Vol. 47, No. 1, 123\u2013144, 2017.","journal-title":"Artificial Intelligence Review"},{"issue":"2","key":"195_CR37","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1145\/276305.276312","volume":"27","author":"S Guha","year":"1998","unstructured":"Guha, S.; Rastogi, R.; Shim, K. CURE: An efficient clustering algorithm for large databases. ACM SIGMOD Record Vol. 27, No. 2, 73\u201384, 1998.","journal-title":"ACM SIGMOD Record"},{"key":"195_CR38","first-page":"1409","volume":"28","author":"R R Sokal","year":"1958","unstructured":"Sokal, R. R. A statistical method for evaluating systematic relationship. University of Kansas Science Bulletin Vol. 28, 1409\u20131438, 1958.","journal-title":"University of Kansas Science Bulletin"},{"key":"195_CR39","unstructured":"DeTone, D.; Malisiewicz, T.; Rabinovich, A. SuperPoint: Self-supervised interest point detection and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 337, 2018."},{"key":"195_CR40","doi-asserted-by":"crossref","unstructured":"Hartley, R.; Zisserman, A. Multiple View Geometry in Computer Vision. Cambridge University Press, 2003.","DOI":"10.1017\/CBO9780511811685"},{"issue":"4","key":"195_CR41","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1093\/comjnl\/20.4.364","volume":"20","author":"D Defays","year":"1977","unstructured":"Defays, D. An efficient algorithm for a complete link method. The Computer Journal Vol. 20, No. 4, 364\u2013366, 1977.","journal-title":"The Computer Journal"},{"key":"195_CR42","doi-asserted-by":"crossref","unstructured":"Nguyen, N.; Caruana, R. Consensus clusterings. In: Proceedings of the IEEE International Conference on Data Mining, 607\u2013612, 2007.","DOI":"10.1109\/ICDM.2007.73"},{"key":"195_CR43","unstructured":"Newcombe, R. A.; Izadi, S.; Hilliges, O.; Molyneaux, D.; Kim, D.; Davison, A. J.; Kohi, P.; Shotton, J.; Hodges, S.; Fitzgibbon, A. KinectFusion: Real-time dense surface mapping and tracking. In: Proceedings of the IEEE International Symposium on Mixed and Augmented Reality, 127\u2013136, 2011."},{"issue":"5","key":"195_CR44","volume":"37","year":"2018","unstructured":"Cao, Y. P.; Kobbelt, L., Hu, S. M. Real-time high-accuracy three-dimensional reconstruction with consumer RGB-D cameras. ACM Transactions on Graphics Vol. 37, No. 5, Article No. 171, 2018.","journal-title":"ACM Transactions on Graphics"},{"key":"195_CR45","doi-asserted-by":"crossref","unstructured":"Song, S.; Yu, F.; Zeng, A.; Chang, A. X.; Savva, M.; Funkhouser, T. Semantic scene completion from a single depth image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1746\u20131754, 2017.","DOI":"10.1109\/CVPR.2017.28"},{"key":"195_CR46","unstructured":"Dosovitskiy, A.; Ros, G.; Codevilla, F.; Lopez, A.; Koltun, V. CARLA: An open urban driving simulator. In: Proceedings of the 1st Annual Conference on Robot Learning, 1\u201316, 2017."},{"key":"195_CR47","unstructured":"K\u00fcmmerle, R.; Grisetti, G.; Strasdat, H.; Konolige, K.; Burgard, W. G2o: A general framework for graph optimization. In: Proceedings of the IEEE International Conference on Robotics and Automation, 3607\u20133613, 2011."},{"key":"195_CR48","first-page":"173","volume-title":"Learning Theory and Kernel Machines. Lecture Notes in Computer Science, Vol. 2777","author":"M Meil\u01ce","year":"2003","unstructured":"Meil\u01ce M. Comparing clusterings by the variation of information. In: Learning Theory and Kernel Machines. Lecture Notes in Computer Science, Vol. 2777. Sch\u00f6lkopf, B.; Warmuth, M.K. Eds. Springer Berlin Heidelberg, 173\u2013187, 2003."},{"issue":"9","key":"195_CR49","doi-asserted-by":"publisher","first-page":"3170","DOI":"10.3390\/s18093170","volume":"18","author":"A Ravankar","year":"2018","unstructured":"Ravankar, A.; Ravankar, A.; Kobayashi, Y.; Hoshino, Y.; Peng, C. C. Path smoothing techniques in robot navigation: State-of-the-art, current and future challenges. Sensors Vol. 18, No. 9, 3170, 2018.","journal-title":"Sensors"},{"key":"195_CR50","doi-asserted-by":"crossref","unstructured":"Murali, V.; Chiu, H.-P.; Samarasekera, S.; Kumar, R. T. Utilizing semantic visual landmarks for precise vehicle navigation. In: Proceedings of the IEEE International Conference on Intelligent Transportation Systems, 1\u20138, 2017.","DOI":"10.1109\/ITSC.2017.8317859"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-020-0195-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s41095-020-0195-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-020-0195-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897406\/10897412.pdf?arnumber=10897412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:38:25Z","timestamp":1762367905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10897412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":50,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1007\/s41095-020-0195-3","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"type":"electronic","value":"2096-0662"},{"type":"print","value":"2096-0433"}],"subject":[],"published":{"date-parts":[[2021,3]]},"assertion":[{"value":"9 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}