{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:39:37Z","timestamp":1740145177956,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"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":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s11554-023-01259-x","type":"journal-article","created":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T13:05:44Z","timestamp":1675343144000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["DeepPilot4Pose: a fast pose localisation for MAV indoor flight using the OAK-D camera"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9440-9944","authenticated-orcid":false,"given":"L. Oyuki","family":"Rojas-Perez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8914-1904","authenticated-orcid":false,"given":"Jose","family":"Martinez-Carranza","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,2]]},"reference":[{"key":"1259_CR1","unstructured":"Oak-d: Hardware specifications. https:\/\/docs.luxonis.com\/projects\/hardware\/en\/latest\/pages\/BW1098OAK.html. Accessed 14 Aug 2022"},{"key":"1259_CR2","doi-asserted-by":"crossref","unstructured":"Balntas, V., Li, S., Prisacariu, V.: Relocnet: continuous metric learning relocalisation using neural nets. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 751\u2013767 (2018)","DOI":"10.1007\/978-3-030-01264-9_46"},{"key":"1259_CR3","doi-asserted-by":"crossref","unstructured":"Blanton, H., Workman, S., Jacobs, N.: A structure-aware method for direct pose estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2019\u20132028 (2022)","DOI":"10.1109\/WACV51458.2022.00028"},{"key":"1259_CR4","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Krull, A., Nowozin, S., Shotton, J., Michel, F., Gumhold, S., Rother, C.: Dsac-differentiable ransac for camera localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6684\u20136692 (2017)","DOI":"10.1109\/CVPR.2017.267"},{"key":"1259_CR5","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Rother, C.: Learning less is more-6d camera localization via 3d surface regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4654\u20134662 (2018)","DOI":"10.1109\/CVPR.2018.00489"},{"issue":"3","key":"1259_CR6","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1111\/mice.12714","volume":"37","author":"J Chen","year":"2022","unstructured":"Chen, J., Li, S., Liu, D., Lu, W.: Indoor camera pose estimation via style-transfer 3d models. Comput. Aided Civ. Infrastruct. Eng. 37(3), 335\u2013353 (2022)","journal-title":"Comput. Aided Civ. Infrastruct. Eng."},{"key":"1259_CR7","doi-asserted-by":"crossref","unstructured":"Civera, J., Grasa, O.G., Davison, A.J., Montiel, J.: 1-point ransac for ekf-based structure from motion. In: 2009 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3498\u20133504. IEEE (2009)","DOI":"10.1109\/IROS.2009.5354410"},{"issue":"6","key":"1259_CR8","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1109\/TPAMI.2007.1049","volume":"29","author":"AJ Davison","year":"2007","unstructured":"Davison, A.J., Reid, I.D., Molton, N.D., Stasse, O.: Monoslam: real-time single camera slam. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1052\u20131067 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1259_CR9","doi-asserted-by":"crossref","unstructured":"Do, T., Miksik, O., DeGol, J., Park, H.S., Sinha, S.N.: Learning to detect scene landmarks for camera localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11132\u201311142 (2022)","DOI":"10.1109\/CVPR52688.2022.01085"},{"key":"1259_CR10","unstructured":"Elmoogy, A., Dong, X., Lu, T., Westendorp, R., Reddy, K.: Pose-gnn: camera pose estimation system using graph neural networks. arXiv preprint arXiv:2103.09435 (2021)"},{"key":"1259_CR11","unstructured":"Gee, A.P.: Incorporating higher level structure in visual slam. Ph.D. thesis, Citeseer (2010)"},{"issue":"11","key":"1259_CR12","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. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"1259_CR13","doi-asserted-by":"crossref","unstructured":"Germain, H., DeTone, D., Pascoe, G., Schmidt, T., Novotny, D., Newcombe, R., Sweeney, C., Szeliski, R., Balntas, V.: Feature query networks: neural surface description for camera pose refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5071\u20135081 (2022)","DOI":"10.1109\/CVPRW56347.2022.00555"},{"key":"1259_CR14","doi-asserted-by":"crossref","unstructured":"Julier, S.J., Uhlmann, J.K.: New extension of the Kalman filter to nonlinear systems. In: Signal Processing, Sensor Fusion, and Target Recognition VI, vol. 3068, pp. 182\u2013193. International Society for Optics and Photonics (1997)","DOI":"10.1117\/12.280797"},{"key":"1259_CR15","doi-asserted-by":"crossref","unstructured":"Kendall, A., Cipolla, R.: Geometric loss functions for camera pose regression with deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5974\u20135983 (2017)","DOI":"10.1109\/CVPR.2017.694"},{"key":"1259_CR16","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: Posenet: a convolutional network for real-time 6-dof camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2938\u20132946 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"1259_CR17","doi-asserted-by":"crossref","unstructured":"Laskar, Z., Melekhov, I., Kalia, S., Kannala, J.: Camera relocalization by computing pairwise relative poses using convolutional neural network. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 929\u2013938 (2017)","DOI":"10.1109\/ICCVW.2017.113"},{"key":"1259_CR18","doi-asserted-by":"crossref","unstructured":"Li, R., Wang, S., Long, Z., Gu, D.: Undeepvo: Monocular visual odometry through unsupervised deep learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 7286\u20137291. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"1259_CR19","unstructured":"Li, X., Ling, H.: Transcamp: Graph transformer for 6-dof camera pose estimation. arXiv preprint arXiv:2105.14065 (2021)"},{"key":"1259_CR20","doi-asserted-by":"publisher","unstructured":"Liu, H., Chen, Q., Pan, N., Sun, Y., An, Y., Pan, D.: Uav stocktaking task-planning for industrial warehouses based on improved hybrid differential evolution algorithm. m. IEEE Transactions on Industrial Informatics 18(1), 582\u2013591 (2022). https:\/\/doi.org\/10.1109\/TII.2021.3054172","DOI":"10.1109\/TII.2021.3054172"},{"key":"1259_CR21","doi-asserted-by":"crossref","unstructured":"Mahendran, S., Ali, H., Vidal, R.: 3d pose regression using convolutional neural networks. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 2174\u20132182 (2017)","DOI":"10.1109\/ICCVW.2017.254"},{"key":"1259_CR22","doi-asserted-by":"crossref","unstructured":"Martinez-Carranza, J., Calway, A., Mayol-Cuevas, W.: Enhancing 6d visual relocalisation with depth cameras. In: 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 899\u2013906. IEEE (2013)","DOI":"10.1109\/IROS.2013.6696457"},{"issue":"2","key":"1259_CR23","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s11370-018-00271-6","volume":"12","author":"H Moon","year":"2019","unstructured":"Moon, H., Martinez-Carranza, J., Cieslewski, T., Faessler, M., Falanga, D., Simovic, A., Scaramuzza, D., Li, S., Ozo, M., De Wagter, C., et al.: Challenges and implemented technologies used in autonomous drone racing. Intell. Serv. Robot. 12(2), 137\u2013148 (2019)","journal-title":"Intell. Serv. Robot."},{"key":"1259_CR24","doi-asserted-by":"crossref","unstructured":"Moreau, A., Gilles, T., Piasco, N., Tsishkou, D., Stanciulescu, B., de La Fortelle, A.: Imposing: implicit pose encoding for efficient camera pose estimation. arXiv preprint arXiv:2205.02638 (2022)","DOI":"10.1109\/WACV56688.2023.00291"},{"issue":"5","key":"1259_CR25","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: Orb-slam: a versatile and accurate monocular slam system. IEEE Trans. Robot. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Robot."},{"key":"1259_CR26","doi-asserted-by":"crossref","unstructured":"Qiao, C., Xiang, Z., Wang, X.: Objects matter: learning object relation graph for robust camera relocalization. arXiv preprint arXiv:2205.13280 (2022)","DOI":"10.2139\/ssrn.4179862"},{"key":"1259_CR27","unstructured":"Quigley, M., Conley, K., Gerkey, B., Faust, J., Foote, T., Leibs, J., Wheeler, R., Ng, A.Y., et al.: Ros: an open-source robot operating system. In: ICRA Workshop on Open Source Software, Kobe, Japan, vol. 3, p. 5 (2009)"},{"issue":"4","key":"1259_CR28","doi-asserted-by":"publisher","first-page":"4407","DOI":"10.1109\/LRA.2018.2869640","volume":"3","author":"N Radwan","year":"2018","unstructured":"Radwan, N., Valada, A., Burgard, W.: Vlocnet++: deep multitask learning for semantic visual localization and odometry. IEEE Robot. Autom. Lett. 3(4), 4407\u20134414 (2018)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"16","key":"1259_CR29","doi-asserted-by":"publisher","first-page":"4524","DOI":"10.3390\/s20164524","volume":"20","author":"LO Rojas-Perez","year":"2020","unstructured":"Rojas-Perez, L.O., Martinez-Carranza, J.: Deeppilot: a cnn for autonomous drone racing. Sensors 20(16), 4524 (2020)","journal-title":"Sensors"},{"issue":"22","key":"1259_CR30","doi-asserted-by":"publisher","first-page":"7436","DOI":"10.3390\/s21227436","volume":"21","author":"LO Rojas-Perez","year":"2021","unstructured":"Rojas-Perez, L.O., Martinez-Carranza, J.: Towards autonomous drone racing without gpu using an oak-d smart camera. Sensors 21(22), 7436 (2021)","journal-title":"Sensors"},{"key":"1259_CR31","unstructured":"Shavit, Y., Ferens, R.: Introduction to camera pose estimation with deep learning. arXiv preprint arXiv:1907.05272 (2019)"},{"key":"1259_CR32","doi-asserted-by":"crossref","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Scene coordinate regression forests for camera relocalization in rgb-d images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2930\u20132937 (2013)","DOI":"10.1109\/CVPR.2013.377"},{"key":"1259_CR33","doi-asserted-by":"crossref","unstructured":"Ummenhofer, B., Zhou, H., Uhrig, J., Mayer, N., Ilg, E., Dosovitskiy, A., Brox, T.: Demon: depth and motion network for learning monocular stereo. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5038\u20135047 (2017)","DOI":"10.1109\/CVPR.2017.596"},{"key":"1259_CR34","doi-asserted-by":"crossref","unstructured":"Valada, A., Radwan, N., Burgard, W.: Deep auxiliary learning for visual localization and odometry. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6939\u20136946. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8462979"},{"key":"1259_CR35","doi-asserted-by":"crossref","unstructured":"Walch, F., Hazirbas, C., Leal-Taixe, L., Sattler, T., Hilsenbeck, S., Cremers, D.: Image-based localization using lstms for structured feature correlation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 627\u2013637 (2017)","DOI":"10.1109\/ICCV.2017.75"},{"key":"1259_CR36","unstructured":"Wan, E.A., Van Der Merwe, R.: The unscented Kalman filter for nonlinear estimation. In: Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No. 00EX373), pp. 153\u2013158. IEEE (2000)"},{"key":"1259_CR37","doi-asserted-by":"crossref","unstructured":"Wang, B., Chen, C., Lu, C.X., Zhao, P., Trigoni, N., Markham, A.: Atloc: attention guided camera localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10393\u201310401 (2020)","DOI":"10.1609\/aaai.v34i06.6608"},{"issue":"9","key":"1259_CR38","doi-asserted-by":"publisher","first-page":"1699","DOI":"10.1109\/TPAMI.2011.41","volume":"33","author":"B Williams","year":"2011","unstructured":"Williams, B., Klein, G., Reid, I.: Automatic relocalization and loop closing for real-time monocular slam. IEEE Trans. Pattern Anal. Mach. Intell. 33(9), 1699\u20131712 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1259_CR39","doi-asserted-by":"crossref","unstructured":"Wu, J., Ma, L., Hu, X.: Delving deeper into convolutional neural networks for camera relocalization. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 5644\u20135651. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989663"},{"key":"1259_CR40","doi-asserted-by":"crossref","unstructured":"Xue, F., Wu, X., Cai, S., Wang, J.: Learning multi-view camera relocalization with graph neural networks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11372\u201311381. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01139"},{"key":"1259_CR41","doi-asserted-by":"crossref","unstructured":"Yang, L., Bai, Z., Tang, C., Li, H., Furukawa, Y., Tan, P.: Sanet: scene agnostic network for camera localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 42\u201351 (2019)","DOI":"10.1109\/ICCV.2019.00013"},{"issue":"4","key":"1259_CR42","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.3390\/s22041383","volume":"22","author":"B Zhao","year":"2022","unstructured":"Zhao, B., Huang, Y., Ci, W., Hu, X.: Unsupervised learning of monocular depth and ego-motion with optical flow features and multiple constraints. Sensors 22(4), 1383 (2022)","journal-title":"Sensors"},{"key":"1259_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, W., Liu, S., Shu, Y., Liu, Y.J.: Towards better generalization: Joint depth-pose learning without posenet. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9151\u20139161 (2020)","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"1259_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Gao, R., Huang, S., Zhu, S.C., Wu, Y.N.: Learning neural representation of camera pose with matrix representation of pose shift via view synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9959\u20139968 (2021)","DOI":"10.1109\/CVPR46437.2021.00983"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-023-01259-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-023-01259-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-023-01259-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T18:32:01Z","timestamp":1677522721000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-023-01259-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["1259"],"URL":"https:\/\/doi.org\/10.1007\/s11554-023-01259-x","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"type":"print","value":"1861-8200"},{"type":"electronic","value":"1861-8219"}],"subject":[],"published":{"date-parts":[[2023,2]]},"assertion":[{"value":"17 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"8"}}