{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:37:56Z","timestamp":1766137076880,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012519"},{"type":"electronic","value":"9783030012526"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01252-6_19","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T13:48:05Z","timestamp":1538747285000},"page":"318-334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Visual-Inertial Object Detection and Mapping"],"prefix":"10.1007","author":[{"given":"Xiaohan","family":"Fei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Soatto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Salas-Moreno, R.F., Newcombe, R.A., Strasdat, H., Kelly, P.H., Davison, A.J.: SLAM++: simultaneous localisation and mapping at the level of objects. In: Computer Vision and Pattern Recognition (CVPR) (2013)","key":"19_CR1","DOI":"10.1109\/CVPR.2013.178"},{"doi-asserted-by":"crossref","unstructured":"Dong, J., Fei, X., Soatto, S.: Visual-inertial-semantic scene representation for 3D object detection. In: Computer Vision and Pattern Recognition (CVPR) (2017)","key":"19_CR2","DOI":"10.1109\/CVPR.2017.380"},{"unstructured":"Jazwinski, A.: Stochastic Processes and Filtering Theory. Academic Press, Cambridge (1970)","key":"19_CR3"},{"doi-asserted-by":"crossref","unstructured":"Mourikis, A., Roumeliotis, S.: A multi-state constraint kalman filter for vision-aided inertial navigation. In: International Conference on Robotics and Automation (ICRA) (2007)","key":"19_CR4","DOI":"10.1109\/ROBOT.2007.364024"},{"doi-asserted-by":"crossref","unstructured":"Tsotsos, K., Chiuso, A., Soatto, S.: Robust inference for visual-inertial sensor fusion. In: International Conference on Robotics and Automation (ICRA) (2015)","key":"19_CR5","DOI":"10.1109\/ICRA.2015.7139924"},{"issue":"5","key":"19_CR6","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1109\/TRO.2008.2003276","volume":"24","author":"J. Civera","year":"2008","unstructured":"Civera, J., Davison, A.J., Montiel, J.M.: Inverse depth parametrization for monocular slam. IEEE Trans. Robot. 24(5), 932\u2013945 (2008)","journal-title":"IEEE Transactions on Robotics"},{"unstructured":"Blake, A., Isard, M.: The condensation algorithm-conditional density propagation and applications to visual tracking. In: Advances in Neural Information Processing Systems (NIPS) (1997)","key":"19_CR7"},{"issue":"7","key":"19_CR8","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1109\/TPAMI.2002.1017620","volume":"24","author":"T. Drummond","year":"2002","unstructured":"Drummond, T., Cipolla, R.: Real-time visual tracking of complex structures. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 24(7), 932\u2013946 (2002)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Klein, G., Murray, D.W.: Full-3D edge tracking with a particle filter. In: British Machine Vision Conference (BMVC) (2006)","key":"19_CR9","DOI":"10.5244\/C.20.114"},{"doi-asserted-by":"crossref","unstructured":"Canny, J.: A computational approach to edge detection. In: Readings in Computer Vision, pp. 184\u2013203. Elsevier (1987)","key":"19_CR10","DOI":"10.1016\/B978-0-08-051581-6.50024-6"},{"doi-asserted-by":"crossref","unstructured":"Gordon, N.J., Salmond, D.J., Smith, A.F.: Novel approach to nonlinear\/non-gaussian bayesian state estimation. In: IEE Proceedings F (Radar and Signal Processing), vol. 140, pp. 107\u2013113. IET (1993)","key":"19_CR11","DOI":"10.1049\/ip-f-2.1993.0015"},{"unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., He, K.: Detectron. https:\/\/github.com\/facebookresearch\/detectron (2018)","key":"19_CR12"},{"key":"19_CR13","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"12","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 12, 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (PAMI)"},{"unstructured":"Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: International Conference on Computer Vision (ICCV) (2001)","key":"19_CR14"},{"doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D slam systems. In: International Conference on Intelligent Robots and Systems (IROS) (2012)","key":"19_CR15","DOI":"10.1109\/IROS.2012.6385773"},{"doi-asserted-by":"crossref","unstructured":"Handa, A., Whelan, T., McDonald, J., Davison, A.J.: A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM. In: International Conference on Robotics and Automation (ICRA) (2014)","key":"19_CR16","DOI":"10.1109\/ICRA.2014.6907054"},{"issue":"11","key":"19_CR17","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. Int. J. Robot. Res. (IJRR) 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res. (IJRR)"},{"issue":"10","key":"19_CR18","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1177\/0278364915620033","volume":"35","author":"M Burri","year":"2016","unstructured":"Burri, M.: The EuRoC micro aerial vehicle datasets. Int. J. Robot. Res. (IJCV) 35(10), 1157\u20131163 (2016)","journal-title":"Int. J. Robot. Res. (IJCV)"},{"doi-asserted-by":"crossref","unstructured":"Pfrommer, B., Sanket, N., Daniilidis, K., Cleveland, J.: Penncosyvio: a challenging visual inertial odometry benchmark. In: International Conference on Robotics and Automation (ICRA) (2017)","key":"19_CR19","DOI":"10.1109\/ICRA.2017.7989443"},{"issue":"2","key":"19_CR20","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"Mark Everingham","year":"2009","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. (IJCV) 88(2), 303\u2013338 (2010)","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"19_CR21","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"Olga Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"International Journal of Computer Vision"},{"key":"19_CR22","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Tsung-Yi Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond pascal: a benchmark for 3D object detection in the wild. In: Winter Conference on Applications of Computer Vision (WACV) (2014)","key":"19_CR23","DOI":"10.1109\/WACV.2014.6836101"},{"key":"19_CR24","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-319-46484-8_10","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Yu Xiang","year":"2016","unstructured":"Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.): ObjectNet3D: a large scale database for 3D object recognition. ECCV 2016. LNCS, vol. 9912, pp. 160\u2013176. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_10"},{"doi-asserted-by":"crossref","unstructured":"Hua, B.S., Pham, Q.H., Nguyen, D.T., Tran, M.K., Yu, L.F., Yeung, S.K.: Scenenn: a scene meshes dataset with annotations. In: 3D Vision (3DV) (2016)","key":"19_CR25","DOI":"10.1109\/3DV.2016.18"},{"unstructured":"Savva, M., et al.: Shrec16 track large-scale 3D shape retrieval from shapenet core55. In: Proceedings of the Eurographics Workshop on 3D Object Retrieval (2016)","key":"19_CR26"},{"doi-asserted-by":"crossref","unstructured":"Whelan, T., Leutenegger, S., Salas-Moreno, R.F., Glocker, B., Davison, A.J.: Elasticfusion: dense slam without a pose graph. In: Robotics: Science and Systems (RSS) (2015)","key":"19_CR27","DOI":"10.15607\/RSS.2015.XI.001"},{"unstructured":"Zhou, Q.Y., Park, J., Koltun, V.: Open3D: a modern library for 3D data processing. arXiv:1801.09847 (2018)","key":"19_CR28"},{"issue":"11","key":"19_CR29","doi-asserted-by":"publisher","first-page":"1548","DOI":"10.1016\/j.imavis.2010.03.009","volume":"28","author":"R.O. Castle","year":"2010","unstructured":"Castle, R.O., Klein, G., Murray, D.W.: Combining monoslam with object recognition for scene augmentation using a wearable camera. Image Vis. Comput. 28(11), 1548\u20131556 (2010)","journal-title":"Image and Vision Computing"},{"doi-asserted-by":"crossref","unstructured":"Civera, J., G\u00e1lvez-L\u00f3pez, D., Riazuelo, L., Tard\u00f3s, J.D., Montiel, J.: Towards semantic slam using a monocular camera. In: International Conference on Intelligent Robots and Systems (IROS) (2011)","key":"19_CR30","DOI":"10.1109\/IROS.2011.6094648"},{"doi-asserted-by":"crossref","unstructured":"Kundu, A., Li, Y., Dellaert, F., Li, F., Rehg, J.: Joint semantic segmentation and 3D reconstruction from monocular video. In: European Conference Computer Vision (ECCV) (2014)","key":"19_CR31","DOI":"10.1007\/978-3-319-10599-4_45"},{"doi-asserted-by":"crossref","unstructured":"Hermans, A., Floros, G., Leibe, B.: Dense 3D semantic mapping of indoor scenes from RGB-D images. In: International Conference on Robotics and Automation (ICRA) (2014)","key":"19_CR32","DOI":"10.1109\/ICRA.2014.6907236"},{"doi-asserted-by":"crossref","unstructured":"Vineet, V.E.A.: Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction. In: International Conference on Robotics and Automation (ICRA) (2015)","key":"19_CR33","DOI":"10.1109\/ICRA.2015.7138983"},{"doi-asserted-by":"crossref","unstructured":"McCormac, J., Handa, A., Davison, A., Leutenegger, S.: Semanticfusion: dense 3D semantic mapping with convolutional neural networks. In: International Conference on Robotics and Automation (ICRA) (2017)","key":"19_CR34","DOI":"10.1109\/ICRA.2017.7989538"},{"doi-asserted-by":"crossref","unstructured":"Bowman, S.L., Atanasov, N., Daniilidis, K., Pappas, G.J.: Probabilistic data association for semantic slam. In: International Conference on Robotics and Automation (ICRA) (2017)","key":"19_CR35","DOI":"10.1109\/ICRA.2017.7989203"},{"doi-asserted-by":"crossref","unstructured":"Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In: International Symposium on Mixed and Augmented Reality (ISMAR) (2007)","key":"19_CR36","DOI":"10.1109\/ISMAR.2007.4538852"},{"doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: International Conference on Computer Vision (ICCV) (2015)","key":"19_CR37","DOI":"10.1109\/ICCV.2015.169"},{"unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS) (2015)","key":"19_CR38"},{"doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: International Conference on Computer Vision (ICCV) (2017)","key":"19_CR39","DOI":"10.1109\/ICCV.2017.322"},{"key":"19_CR40","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Wei Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Computer Vision and Pattern Recognition (CVPR) (2016)","key":"19_CR41","DOI":"10.1109\/CVPR.2016.91"},{"doi-asserted-by":"crossref","unstructured":"Choi, C., Christensen, H.I.: 3D textureless object detection and tracking: An edge-based approach. In: International Conference on Intelligent Robots and Systems (IROS) (2012)","key":"19_CR42","DOI":"10.1109\/IROS.2012.6386065"},{"issue":"1","key":"19_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/0600000001","volume":"1","author":"Vincent Lepetit","year":"2005","unstructured":"Lepetit, V., Fua, P., et al.: Monocular model-based 3D tracking of rigid objects: a survey. In: Foundations and Trends$${\\textregistered }$$ in Computer Graphics and Vision (2005)","journal-title":"Foundations and Trends\u00ae in Computer Graphics and Vision"},{"issue":"3","key":"19_CR44","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s11263-011-0514-3","volume":"98","author":"Victor A. Prisacariu","year":"2012","unstructured":"Prisacariu, V.A., Reid, I.D.: Pwp3D: real-time segmentation and tracking of 3D objects. Int. J. Comput. Vis. (IJCV) 98(3), 335\u2013354 (2012)","journal-title":"International Journal of Computer Vision"},{"doi-asserted-by":"crossref","unstructured":"Tjaden, H., Schwanecke, U., Sch\u00f6mer, E.: Real-time monocular pose estimation of 3D objects using temporally consistent local color histograms. In: Computer Vision and Pattern Recognition (CVPR) (2017)","key":"19_CR45","DOI":"10.1109\/ICCV.2017.23"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01252-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T01:06:00Z","timestamp":1664931960000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01252-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012519","9783030012526"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01252-6_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}