{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:31:41Z","timestamp":1742913101652,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031457241"},{"type":"electronic","value":"9783031457258"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-45725-8_2","type":"book-chapter","created":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T12:02:09Z","timestamp":1697544129000},"page":"21-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semi-automated Generation of\u00a0Accurate Ground-Truth for\u00a03D Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0835-202X","authenticated-orcid":false,"given":"M. H.","family":"Zwemer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9182-2911","authenticated-orcid":false,"given":"D.","family":"Scholte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7639-7716","authenticated-orcid":false,"given":"P. H. N.","family":"de With","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,18]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Ansari, J.A., Sharma, S., Majumdar, A., Jatavallabhula, K.M., Krishna, K.M.: The earth ain\u2019t flat: monocular reconstruction of vehicles on steep and graded roads from a moving camera. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8404\u20138410 (2018). https:\/\/api.semanticscholar.org\/CorpusID:3761728","DOI":"10.1109\/IROS.2018.8593698"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M3D-RPN: monocular 3D region proposal network for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9286\u20139295. IEEE Computer Society, Los Alamitos (2019). https:\/\/doi.ieeecomputersociety.org\/10.1109\/ICCV.2019.00938","DOI":"10.1109\/ICCV.2019.00938"},{"key":"2_CR3","doi-asserted-by":"publisher","unstructured":"Brouwers, G.M.Y.E., Zwemer, M.H., Wijnhoven, R.G.J., de With, P.H.N.: Automatic calibration of stationary surveillance cameras in the wild. In: Proceedings of the IEEE CVPR (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_52","DOI":"10.1007\/978-3-319-48881-3_52"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Y., Li, B., Jiao, Z., Li, H., Zeng, X., Wang, X.: Monocular 3D object detection with decoupled structured polygon estimation and height-guided depth estimation. In: AAAI (2020). https:\/\/arxiv.org\/abs\/2002.01619","DOI":"10.1609\/aaai.v34i07.6618"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Chabot, F., Chaouch, M., Rabarisoa, J., Teuli\u00e8re, C., Chateau, T.: Deep MANTA: a coarse-to-fine many-task network for joint 2D and 3D vehicle analysis from monocular image. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1827\u20131836. IEEE Computer Society, Los Alamitos (2017). https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR.2017.198","DOI":"10.1109\/CVPR.2017.198"},{"key":"2_CR6","doi-asserted-by":"publisher","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 CVPR (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.236","DOI":"10.1109\/CVPR.2016.236"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Choe, J., Joo, K., Rameau, F., Shim, G., Kweon, I.S.: Segment2Regress: monocular 3D vehicle localization in two stages. In: Robotics: Science and Systems (2019). https:\/\/doi.org\/10.15607\/RSS.2019.XV.016","DOI":"10.15607\/RSS.2019.XV.016"},{"key":"2_CR8","doi-asserted-by":"publisher","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 886\u2013893. IEEE (2005). https:\/\/doi.org\/10.1109\/CVPR.2005.177","DOI":"10.1109\/CVPR.2005.177"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Ding, M., Huo, Y., Yi, H., Wang, Z., Shi, J., Lu, Z., Luo, P.: Learning depth-guided convolutions for monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on CVPR (2020). https:\/\/arxiv.org\/abs\/1912.04799","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"2_CR10","doi-asserted-by":"publisher","unstructured":"Dubsk\u00e1, M., Herout, A., Sochor, J.: Automatic camera calibration for traffic understanding. In: BMVC, vol. 4, 6, p. 8 (2014). https:\/\/doi.org\/10.5244\/C.28.42","DOI":"10.5244\/C.28.42"},{"key":"2_CR11","unstructured":"Fang, J., Zhou, L., Liu, G.: 3D bounding box estimation for autonomous vehicles by cascaded geometric constraints and depurated 2D detections using 3D results (2019). https:\/\/arxiv.org\/abs\/1909.01867"},{"key":"2_CR12","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/3-540-45103-X_50","volume-title":"Image Analysis","author":"G Farneb\u00e4ck","year":"2003","unstructured":"Farneb\u00e4ck, G.: Two-frame motion estimation based on polynomial expansion. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 363\u2013370. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-45103-X_50"},{"key":"2_CR13","doi-asserted-by":"publisher","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: Conference on CVPR (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015). https:\/\/arxiv.org\/abs\/1504.08083","DOI":"10.1109\/ICCV.2015.169"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE ICCV (2017). https:\/\/arxiv.org\/abs\/1703.06870","DOI":"10.1109\/ICCV.2017.322"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"He, T., Soatto, S.: Mono3D++: monocular 3D vehicle detection with two-scale 3D hypotheses and task priors. CoRR abs\/1901.03446 (2019). https:\/\/arxiv.org\/abs\/1901.03446","DOI":"10.1609\/aaai.v33i01.33018409"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Kehl, W., Manhardt, F., Tombari, F., Ilic, S., Navab, N.: SSD-6D: making RGB-based 3D detection and 6D pose estimation great again. In: Proceedings of the IEEE ICCV, pp. 1521\u20131529 (2017). https:\/\/arxiv.org\/abs\/1711.10006","DOI":"10.1109\/ICCV.2017.169"},{"key":"2_CR18","doi-asserted-by":"publisher","unstructured":"Kundu, A., Li, Y., Rehg, J.M.: 3D-RCNN: instance-level 3D object reconstruction via render-and-compare. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3559\u20133568 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00375","DOI":"10.1109\/CVPR.2018.00375"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Li, B., Ouyang, W., Sheng, L., Zeng, X., Wang, X.: GS3D: an efficient 3D object detection framework for autonomous driving, 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1019\u20131028. IEEE Computer Society, Los Alamitos (2019). https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR.2019.00111","DOI":"10.1109\/CVPR.2019.00111"},{"key":"2_CR20","unstructured":"Li, P.: Monocular 3D detection with geometric constraints embedding and semi-supervised training (2020). https:\/\/arxiv.org\/abs\/2009.00764"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: RTM3D: real-time monocular 3D detection from object keypoints for autonomous driving. arXiv preprint arXiv:2001.03343 (2020)","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"2_CR22","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. CoRR arXiv:abs\/1405.0312 (2014). https:\/\/dblp.org\/rec\/bib\/journals\/corr\/LinMBHPRDZ14"},{"key":"2_CR23","doi-asserted-by":"publisher","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: SMOKE: single-stage monocular 3D object detection via keypoint estimation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 4289\u20134298 (2020). https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00506","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Ma, X., Wang, Z., Li, H., Zhang, P., Ouyang, W., Fan, X.: Accurate monocular 3D object detection via color-embedded 3D reconstruction for autonomous driving. In: Proceedings of the IEEE ICCV (2019). https:\/\/arxiv.org\/abs\/1903.11444","DOI":"10.1109\/ICCV.2019.00695"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Kosecka, 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 Computer Society, Los Alamitos (2017). ISSN:1063-6919. https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR.2017.597","DOI":"10.1109\/CVPR.2017.597"},{"key":"2_CR26","doi-asserted-by":"publisher","unstructured":"Nilsson, M., Ard\u00f6, H.: In search of a car - utilizing a 3D model with context for object detection. In: Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014), pp. 419\u2013424. INSTICC, SciTePress (2014). https:\/\/doi.org\/10.5220\/0004685304190424","DOI":"10.5220\/0004685304190424"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Qin, Z., Wang, J., Lu, Y.: Monogrnet: a geometric reasoning network for monocular 3D object localization. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019). https:\/\/arxiv.org\/abs\/1811.10247","DOI":"10.1609\/aaai.v33i01.33018851"},{"key":"2_CR28","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)"},{"key":"2_CR29","unstructured":"Roddick, T., Kendall, A., Cipolla, R.: Orthographic feature transform for monocular 3D object detection. arXiv:1811.08188 (2018)"},{"key":"2_CR30","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.cviu.2017.05.015","volume":"161","author":"J Sochor","year":"2017","unstructured":"Sochor, J., Jur\u00e1nek, R., Herout, A.: Traffic surveillance camera calibration by 3D model bounding box alignment for accurate vehicle speed measurement. Comput. Vis. Image Underst. 161, 87\u201398 (2017). https:\/\/arxiv.org\/abs\/1702.06451","journal-title":"Comput. Vis. Image Underst."},{"issue":"1","key":"2_CR31","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/TITS.2018.2799228","volume":"20","author":"J Sochor","year":"2018","unstructured":"Sochor, J., \u0160pa\u0148hel, J., Herout, A.: Boxcars: Improving fine-grained recognition of vehicles using 3-D bounding boxes in traffic surveillance. IEEE Trans. Intell. Transp. Syst. 20(1), 97\u2013108 (2018). https:\/\/arxiv.org\/abs\/1703.00686","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Srivastava, S., Jurie, F., Sharma, G.: Learning 2D to 3D lifting for object detection in 3D for autonomous vehicles. arXiv preprint arXiv:1904.08494 (2019)","DOI":"10.1109\/IROS40897.2019.8967624"},{"issue":"8","key":"2_CR33","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1016\/S0262-8856(97)00009-7","volume":"15","author":"GD Sullivan","year":"1997","unstructured":"Sullivan, G.D., Baker, K.D., Worrall, A.D., Attwood, C., Remagnino, P.: Model-based vehicle detection and classification using orthographic approximations. Image Vis. Comput. 15(8), 649\u2013654 (1997). https:\/\/doi.org\/10.1016\/S0262-8856(97)00009-7","journal-title":"Image Vis. Comput."},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Yin, W., Kong, T., Jiang, Y., Li, L., Shen, C.: Task-aware monocular depth estimation for 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020). https:\/\/arxiv.org\/abs\/1909.07701","DOI":"10.1609\/aaai.v34i07.6908"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.Q.: Pseudo-lidar from visual depth estimation: bridging the gap in 3D object detection for autonomous driving. CoRR abs\/1812.07179 (2018). https:\/\/arxiv.org\/abs\/1812.07179","DOI":"10.1109\/CVPR.2019.00864"},{"key":"2_CR37","doi-asserted-by":"publisher","unstructured":"Weber, M., F\u00fcrst, M., Z\u00f6llner, J.M.: Direct 3D detection of vehicles in monocular images with a CNN based 3D decoder. In: 2019 IEEE Intelligent Vehicles Symposium (IV), pp. 417\u2013423 (2019). https:\/\/doi.org\/10.1109\/IVS.2019.8814198","DOI":"10.1109\/IVS.2019.8814198"},{"key":"2_CR38","doi-asserted-by":"publisher","unstructured":"Wijnhoven, R.G.J., de With, P.H.N.: Unsupervised sub-categorization for object detection: finding cars from a driving vehicle. In: 2011 IEEE ICCV Workshops, pp. 2077\u20132083. IEEE (2011). https:\/\/doi.org\/10.1109\/ICCVW.2011.6130504","DOI":"10.1109\/ICCVW.2011.6130504"},{"key":"2_CR39","unstructured":"You, Y., et al.: Pseudo-lidar++: accurate depth for 3D object detection in autonomous driving. CoRR abs\/1906.06310 (2019). https:\/\/arxiv.org\/abs\/1906.06310"},{"key":"2_CR40","doi-asserted-by":"publisher","unstructured":"Zwemer, M.H., Scholte, D., Wijnhoven, R.G.J., de With, P.H.N.: 3D detection of vehicles from 2D images in traffic surveillance. In: Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, pp. 97\u2013106. INSTICC, SciTePress (2022). https:\/\/doi.org\/10.5220\/0010783600003124","DOI":"10.5220\/0010783600003124"}],"container-title":["Communications in Computer and Information Science","Computer Vision, Imaging and Computer Graphics Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-45725-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T12:08:50Z","timestamp":1697544530000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-45725-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031457241","9783031457258"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-45725-8_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"VISIGRAPP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Conference on Computer Vision, Imaging and Computer Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 February 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 February 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"visigrapp2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/visigrapp.scitevents.org\/?y=2022","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}