{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T01:35:14Z","timestamp":1767317714906,"version":"3.48.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032119025","type":"print"},{"value":"9783032119032","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-11903-2_19","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T01:32:18Z","timestamp":1767317538000},"page":"243-256","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Refined 3D Object Localization with Monocular Camera Using Depth Estimation and Geometric Refinement"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6332-1002","authenticated-orcid":false,"given":"Thanh Nguyen","family":"Canh","sequence":"first","affiliation":[]},{"given":"Quang Minh","family":"Trinh","sequence":"additional","affiliation":[]},{"given":"Thai-Viet","family":"Dang","sequence":"additional","affiliation":[]},{"given":"Phan Xuan","family":"Tan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7524-6529","authenticated-orcid":false,"given":"Xiem","family":"HoangVan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"19_CR1","first-page":"2147","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"X Chen","year":"2016","unstructured":"Chen, X., et al.: Monocular 3d object detection for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147\u20132156 (2016)"},{"key":"19_CR2","doi-asserted-by":"publisher","first-page":"13018","DOI":"10.1109\/ICRA48506.2021.9561423","volume-title":"2021 IEEE International Conference on Robotics and Automation (ICRA)","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Wang, L., Liu, M.: Yolostereo3d: a step back to 2d for efficient stereo 3d detection. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13018\u201313024. IEEE (2021)"},{"key":"19_CR3","first-page":"7776","volume-title":"International Conference on Robotics and Automation (ICRA)","author":"Y Jung","year":"2023","unstructured":"Jung, Y., Seo, S.-W., Kim, S.-W.: Fast point clouds up sampling with uncertainty quantification for autonomous vehicles. In: International Conference on Robotics and Automation (ICRA), pp. 7776\u20137782. IEEE (2023)"},{"issue":"3","key":"19_CR4","doi-asserted-by":"publisher","first-page":"533","DOI":"10.3390\/electronics12030533","volume":"12","author":"T-V Dang","year":"2023","unstructured":"Dang, T.-V., Bui, N.-T.: Multi-scale fully convolutional network-based semantic segmentation for mobile robot navigation. Electronics. 12(3), 533 (2023)","journal-title":"Electronics"},{"issue":"15","key":"19_CR5","doi-asserted-by":"publisher","first-page":"6907","DOI":"10.3390\/s23156907","volume":"23","author":"T-V Dang","year":"2023","unstructured":"Dang, T.-V., Tran, D.-M.-C., Tan, P.X.: IRDC-net: lightweight semantic SEG mentation network based on monocular camera for mobile robot navigation. Sensors. 23(15), 6907 (2023)","journal-title":"Sensors"},{"key":"19_CR6","first-page":"3","volume-title":"International Symposium on Information and Communication Technology","author":"V-T Nguyen","year":"2024","unstructured":"Nguyen, V.-T., Bui, N.-N., Tran, D.-M.-C., Dang, T.-V., Tan, P.X.: FDE-net: lightweight depth estimation for monocular cameras. In: International Symposium on Information and Communication Technology, pp. 3\u201313. Springer (2024)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Van, X.H., Do, N.: An efficient regression method for 3d object localization in machine vision systems. IAES Int. J. Robotics Automat. 11(2) (2022)","DOI":"10.11591\/ijra.v11i2.pp111-121"},{"issue":"3","key":"19_CR8","doi-asserted-by":"publisher","first-page":"53","DOI":"10.14313\/jamris-2025-025","volume":"19","author":"TN Canh","year":"2025","unstructured":"Canh, T.N., Trinh Ngoc, D., HoangVan, X.: Monocular 3d object localization using 2d estimates for industrial robot vision system. J. Automat. Mobile Robotics Intell. Syst. 19(3), 53\u201365 (2025)","journal-title":"J. Automat. Mobile Robotics Intell. Syst."},{"key":"19_CR9","first-page":"4012","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K-C Huang","year":"2022","unstructured":"Huang, K.-C., Wu, T.-H., Su, H.-T., Hsu, W.H.: MonoDTR: monocular 3d object detection with depth-aware transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4012\u20134021 (2022)"},{"key":"19_CR10","first-page":"10248","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Yan","year":"2024","unstructured":"Yan, L., Yan, P., Xiong, S., Xiang, X., Tan, Y.: MONOCD: monocular 3d object detection with complementary depths. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10248\u201310257 (2024)"},{"issue":"11","key":"19_CR11","doi-asserted-by":"publisher","first-page":"7464","DOI":"10.1109\/LRA.2023.3313053","volume":"8","author":"K Xiong","year":"2023","unstructured":"Xiong, K., et al.: You only look bottom-up for monocular 3d object detection. IEEE Robotics Automat. Lett. 8(11), 7464\u20137471 (2023)","journal-title":"IEEE Robotics Automat. Lett."},{"issue":"6","key":"19_CR12","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR13","first-page":"21","volume-title":"European Conference on Computer Vision","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: European Conference on Computer Vision, pp. 21\u201337. Springer (2016)"},{"key":"19_CR14","first-page":"779","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Redmon","year":"2016","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)"},{"key":"19_CR15","unstructured":"Jocher, G., Qiu, J., Chaurasia, A.: Ultralytics YOLO, https:\/\/github.com\/ultralytics\/ultralytics. Last accessed 12 Mar 2025"},{"key":"19_CR16","unstructured":"Nguyen, Q.T., Canh, T.N., HoangVan, X.: Enhancing depth image estimation for underwater robots by combining image processing and machine learning. arXiv preprint arXiv:2411.05344. (2024)"},{"key":"19_CR17","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., Muller, M.: Zoedepth: zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288. (2023)"},{"key":"19_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109982","volume":"145","author":"S Tang","year":"2024","unstructured":"Tang, S., Lu, T., Liu, X., Zhou, H., Zhang, Y.: CATNET: convolutional attention and transformer for monocular depth estimation. Pattern Recogn. 145, 109982 (2024)","journal-title":"Pattern Recogn."},{"key":"19_CR19","doi-asserted-by":"publisher","first-page":"6101","DOI":"10.1109\/ICRA.2019.8794182","volume-title":"International Conference on Robotics and Automation (ICRA)","author":"D Wofk","year":"2019","unstructured":"Wofk, D., Ma, F., Yang, T.-J., Karaman, S., Sze, V.: Fastdepth: fast monocular depth estimation on embedded systems. In: International Conference on Robotics and Automation (ICRA), pp. 6101\u20136108. IEEE (2019)"},{"key":"19_CR20","first-page":"1","volume-title":"International Conference on System Science and Engineering (ICSSE)","author":"TN Canh","year":"2024","unstructured":"Canh, T.N., DoNgoc, M., Quang, T.N., Thanh, H.B., HoangVan, X.: Underwater image enhancement for depth estimation via various image processing techniques. In: International Conference on System Science and Engineering (ICSSE), pp. 1\u20136. IEEE (2024)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Dang, T.-V., Bui, N.-N., Tan, P.X.: KD-SegNet: efficient semantic segmentation network with knowledge distillation based on monocular camera. Comput. Mater. Continua. 82(2) (2025)","DOI":"10.32604\/cmc.2025.060605"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Dang, T.-V., Tran, C., Bui, N.-N., Tan, P.: ELDE-net: efficient light-weight depth estimation network for deep reinforcement learning-based mobile robot path planning. Comput. Mater. Continua, 1\u201330 (2025)","DOI":"10.32604\/cmc.2025.067500"},{"key":"19_CR23","first-page":"746","volume-title":"European Conference on Computer Vision","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: European Conference on Computer Vision, pp. 746\u2013760. Springer (2012)"},{"issue":"11","key":"19_CR24","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. Robotics Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robotics Res."}],"container-title":["Lecture Notes in Computer Science","Interactive Collaborative Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-11903-2_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T01:32:20Z","timestamp":1767317540000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-11903-2_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032119025","9783032119032"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-11903-2_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Interactive Collaborative Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icr2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lqdtu.edu.vn\/page\/Home\/ICR-2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}