{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:15:30Z","timestamp":1775578530935,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012151","type":"print"},{"value":"9783030012168","type":"electronic"}],"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\/978-3-030-01216-8_40","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T15:10:26Z","timestamp":1539011426000},"page":"664-679","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":118,"title":["Stereo Vision-Based Semantic 3D Object and Ego-Motion Tracking for Autonomous Driving"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5839-8777","authenticated-orcid":false,"given":"Peiliang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0994-9816","authenticated-orcid":false,"given":"Tong","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5573-2909","authenticated-orcid":false,"given":"Shaojie","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"40_CR1","unstructured":"Chen, X., et al.: 3D object proposals for accurate object class detection. In: Advances in Neural Information Processing Systems, pp. 424\u2013432 (2015)"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Qin, T., Li, P., Shen, S.: VINS-Mono: a robust and versatile monocular visual-inertial state estimator. arXiv preprint arXiv:1708.03852 (2017)","DOI":"10.1109\/TRO.2018.2853729"},{"issue":"5","key":"40_CR4","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., Tard\u00f3s, J.D.: ORB-SLAM2: an open-source SLAM system for monocular, stereo and RGB-D cameras. IEEE Trans. Robot. 33(5), 1255\u20131262 (2017)","journal-title":"IEEE Trans. Robot."},{"key":"40_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10605-2_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Engel","year":"2014","unstructured":"Engel, J., Sch\u00f6ps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54"},{"key":"40_CR6","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, pp. 91\u201399 (2015)"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Frost, D.P., K\u00e4hler, O., Murray, D.W.: Object-aware bundle adjustment for correcting monocular scale drift. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 4770\u20134776. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487680"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Sucar, E., Hayet, J.B.: Probabilistic global scale estimation for monoslam based on generic object detection. In: Computer Vision and Pattern Recognition Workshops (CVPRW) (2017)","DOI":"10.1109\/CVPRW.2017.135"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Bowman, S.L., Atanasov, N., Daniilidis, K., Pappas, G.J.: Probabilistic data association for semantic slam. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 1722\u20131729. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989203"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Atanasov, N., Zhu, M., Daniilidis, K., Pappas, G.J.: Semantic localization via the matrix permanent. In: Proceedings of Robotics: Science and Systems, vol. 2 (2014)","DOI":"10.15607\/RSS.2014.X.043"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Pillai, S., Leonard, J.J.: Monocular slam supported object recognition. In: Proceedings of Robotics: Science and Systems, vol. 2 (2015)","DOI":"10.15607\/RSS.2015.XI.034"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Dong, J., Fei, X., Soatto, S.: Visual-inertial-semantic scene representation for 3-D object detection. arXiv preprint arXiv:1606.03968 (2016)","DOI":"10.1109\/CVPR.2017.380"},{"key":"40_CR13","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: 2011 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1277\u20131284. IEEE (2011)","DOI":"10.1109\/IROS.2011.6094648"},{"key":"40_CR14","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: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1352\u20131359. IEEE (2013)","DOI":"10.1109\/CVPR.2013.178"},{"key":"40_CR15","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1016\/j.robot.2015.08.009","volume":"75","author":"D G\u00e1lvez-L\u00f3pez","year":"2016","unstructured":"G\u00e1lvez-L\u00f3pez, D., Salas, M., Tard\u00f3s, J.D., Montiel, J.: Real-time monocular object slam. Robot. Auton. Syst. 75, 435\u2013449 (2016)","journal-title":"Robot. Auton. Syst."},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Bao, S.Y., Savarese, S.: Semantic structure from motion. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2025\u20132032. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995462"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Bao, S.Y., Bagra, M., Chao, Y.W., Savarese, S.: Semantic structure from motion with points, regions, and objects. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2703\u20132710. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247992"},{"key":"40_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1007\/978-3-319-10599-4_45","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Kundu","year":"2014","unstructured":"Kundu, A., Li, Y., Dellaert, F., Li, F., Rehg, J.M.: Joint semantic segmentation and 3D reconstruction from monocular video. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 703\u2013718. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_45"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Vineet, V., et al.: Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 75\u201382. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7138983"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., Belaroussi, R.: Semi-dense 3D semantic mapping from monocular slam. arXiv preprint arXiv:1611.04144 (2016)","DOI":"10.1109\/ITSC.2017.8317942"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"McCormac, J., Handa, A., Davison, A., Leutenegger, S.: Semanticfusion: Dense 3D semantic mapping with convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 4628\u20134635. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989538"},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Bao, S.Y., Chandraker, M., Lin, Y., Savarese, S.: Dense object reconstruction with semantic priors. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1264\u20131271. IEEE (2013)","DOI":"10.1109\/CVPR.2013.167"},{"issue":"11","key":"40_CR23","doi-asserted-by":"publisher","first-page":"2608","DOI":"10.1109\/TPAMI.2013.87","volume":"35","author":"MZ Zia","year":"2013","unstructured":"Zia, M.Z., Stark, M., Schiele, B., Schindler, K.: Detailed 3D representations for object recognition and modeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(11), 2608\u20132623 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Choi, W., Lin, Y., Savarese, S.: Data-driven 3D voxel patterns for object category recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1903\u20131911 (2015)","DOI":"10.1109\/CVPR.2015.7298800"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Ko\u0161eck\u00e1, J.: 3D bounding box estimation using deep learning and geometry. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5632\u20135640. IEEE (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"40_CR27","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: Orb: an efficient alternative to sift or surf. In: 2011 IEEE international conference on Computer Vision (ICCV), pp. 2564\u20132571. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"40_CR28","unstructured":"Gu, T.: Improved trajectory planning for on-road self-driving vehicles via combined graph search, optimization and topology analysis. Ph.D. thesis, Carnegie Mellon University (2017)"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"40_CR30","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. (IJRR) (2013)","DOI":"10.1177\/0278364913491297"},{"key":"40_CR31","unstructured":"Cordts, M., et al.: The cityscapes dataset. In: CVPR Workshop on the Future of Datasets in Vision, vol, 1, March 2015"},{"key":"40_CR32","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: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 573\u2013580. IEEE (2012)","DOI":"10.1109\/IROS.2012.6385773"}],"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\/978-3-030-01216-8_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:28:45Z","timestamp":1665188925000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01216-8_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012151","9783030012168"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01216-8_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 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"}]}}