{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:56:34Z","timestamp":1740182194036,"version":"3.37.3"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T00:00:00Z","timestamp":1658793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100016258","name":"Institute of Civil-Military Technology Cooperation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100016258","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003626","name":"Defense Acquisition Program Administration","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003626","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy, Korea","doi-asserted-by":"publisher","award":["20-SN-GU-01"],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,27]]},"abstract":"Abstract<\/jats:title>\n This paper presents a novel deep learning-based camera localization method using iterative relative pose estimation to improve the accuracy of pose estimation from a single RGB image. Although most existing deep learning-based camera localization methods are more robust for textureless cases, illumination changes, and occlusions, they are less accurate than other non-deep learning-based methods. The proposed method improved the localization accuracy by using the relative poses between the input image and the training dataset images. It simultaneously trained the network for the absolute poses of the input images and their relative poses using Siamese networks. In the inference stage, it estimated the absolute pose of a query image and iteratively updated the pose using relative pose information. Real world examples with widely used camera localization datasets and our dataset were utilized to validate the performance of the proposed method, which exhibited higher localization accuracy than the state-of-the-art deep learning-based camera localization methods. In the end, the application of the proposed method to augmented reality was presented.<\/jats:p>","DOI":"10.1093\/jcde\/qwac066","type":"journal-article","created":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T17:00:06Z","timestamp":1658854806000},"page":"1482-1497","source":"Crossref","is-referenced-by-count":0,"title":["Camera localization with Siamese neural networks using iterative relative pose estimation"],"prefix":"10.1093","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9436-3448","authenticated-orcid":false,"given":"Daewoon","family":"Kim","sequence":"first","affiliation":[{"name":"The School of Mechanical Engineering, Gwangju Institute of Science and Technology (GIST) , Gwangju 61005, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7668-5796","authenticated-orcid":false,"given":"Kwanghee","family":"Ko","sequence":"additional","affiliation":[{"name":"The School of Mechanical Engineering, Gwangju Institute of Science and Technology (GIST) , Gwangju 61005, Republic of Korea"}]}],"member":"286","published-online":{"date-parts":[[2022,7,26]]},"reference":[{"key":"2022082710080515500_bib39","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1007\/978-3-030-01264-9_46","article-title":"Relocnet: Continuous metric learning relocalisation using neural nets","volume-title":"Proceedings of the 2018 European Conference on Computer Vision (ECCV)","author":"Balntas","year":"2018"},{"key":"2022082710080515500_bib2","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","article-title":"Speeded-up robust features (SURF)","volume":"110","author":"Bay","year":"2008","journal-title":"Computer Vision and Image Understanding"},{"key":"2022082710080515500_bib30","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.1109\/CVPR.2018.00277","article-title":"Geometry-aware learning of maps for camera localization","volume-title":"Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Brahmbhatt","year":"2018"},{"key":"2022082710080515500_bib28","doi-asserted-by":"crossref","first-page":"4290","DOI":"10.1109\/ICRA.2014.6907483","article-title":"Eliminating conditionally independent sets in factor graphs: A unifying perspective based on smart factors","volume-title":"2014 IEEE International Conference on Robotics and Automation (ICRA)","author":"Carlone","year":"2014"},{"key":"2022082710080515500_bib8","first-page":"574","article-title":"Real-time tracking of complex structures with on-line camera calibration","volume-title":"Proceedings of the British Machine Vision Conference (BMVC\u201999)","author":"Drummond","year":"1999"},{"key":"2022082710080515500_bib13","doi-asserted-by":"crossref","first-page":"1440","DOI":"10.1109\/ICCV.2015.169","article-title":"Fast R-CNN","volume-title":"Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV)","author":"Girshick","year":"2015"},{"key":"2022082710080515500_bib31","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/MITS.2010.939925","article-title":"A tutorial on graph-based SLAM","volume":"2","author":"Grisetti","year":"2010","journal-title":"IEEE Intelligent Transportation Systems Magazine"},{"key":"2022082710080515500_bib41","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"2022082710080515500_bib26","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"2022082710080515500_bib20","doi-asserted-by":"crossref","first-page":"2938","DOI":"10.1109\/ICCV.2015.336","article-title":"PoseNet: A convolutional network for real-time 6-DoF camera relocalization","volume-title":"Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV)","author":"Kendall","year":"2015"},{"key":"2022082710080515500_bib44","doi-asserted-by":"crossref","first-page":"4762","DOI":"10.1109\/ICRA.2016.7487679","article-title":"Modelling uncertainty in deep learning for camera relocalization","volume-title":"Proceedings of the 2016 IEEE International Conference on Robotics and Automation (ICRA)","author":"Kendall","year":"2016"},{"key":"2022082710080515500_bib29","doi-asserted-by":"crossref","first-page":"5974","DOI":"10.1109\/CVPR.2017.694","article-title":"Geometric loss functions for camera pose regression with deep learning","volume-title":"Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Kendall","year":"2017"},{"key":"2022082710080515500_bib9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cad.2017.12.003","article-title":"Development of an AR based method for augmentation of 3D CAD data onto a real ship block image","volume":"98","author":"Kim","year":"2018","journal-title":"Computer-Aided Design"},{"key":"2022082710080515500_bib43","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv preprint","author":"Kingma","year":"2014"},{"key":"2022082710080515500_bib12","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Advances in neural information processing systems","author":"Krizhevsky","year":"2012"},{"key":"2022082710080515500_bib40","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1109\/ICCVW.2017.113","article-title":"Camera relocalization by computing pairwise relative poses using convolutional neural network","volume-title":"Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops\u00a0(ICCVW)","author":"Laskar","year":"2017"},{"key":"2022082710080515500_bib3","doi-asserted-by":"crossref","first-page":"2548","DOI":"10.1109\/ICCV.2011.6126542","article-title":"BRISK: Binary robust invariant scalable keypoints","volume-title":"Proceedings of the 2011 International Conference on Computer Vision","author":"Leutenegger","year":"2011"},{"key":"2022082710080515500_bib37","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1080\/10095020.2021.1960779","article-title":"VNLSTM-PoseNet: A novel deep convnet for real-time 6-DoF camera relocalization in urban streets","volume":"24","author":"Li","year":"2021","journal-title":"Geo-spatial Information Science"},{"key":"2022082710080515500_bib10","doi-asserted-by":"crossref","first-page":"2372","DOI":"10.1109\/ICCV.2017.260","article-title":"Efficient global 2D\u20133D matching for camera localization in a large-scale 3D map","volume-title":"Proceedings of the 2017 IEEE International Conference on Computer Vision\u00a0(ICCV)","author":"Liu","year":"2017"},{"key":"2022082710080515500_bib19","doi-asserted-by":"crossref","first-page":"102600","DOI":"10.1016\/j.scs.2020.102600","article-title":"Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection","volume":"65","author":"Loey","year":"2021","journal-title":"Sustainable Cities and Society"},{"key":"2022082710080515500_bib14","doi-asserted-by":"crossref","first-page":"3431","DOI":"10.1109\/CVPR.2015.7298965","article-title":"Fully convolutional networks for semantic segmentation","volume-title":"Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Long","year":"2015"},{"key":"2022082710080515500_bib32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1486525.1486527","article-title":"SBA: A software package for generic sparse bundle adjustment","volume":"36","author":"Lourakis","year":"2009","journal-title":"ACM Transactions on Mathematical Software (TOMS)"},{"key":"2022082710080515500_bib1","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"International Journal of Computer Vision"},{"key":"2022082710080515500_bib17","doi-asserted-by":"crossref","first-page":"103719","DOI":"10.1016\/j.autcon.2021.103719","article-title":"Presenting the best prediction model of water inflow into drill and blast tunnels among several machine learning techniques","volume":"127","author":"Mahmoodzadeh","year":"2021","journal-title":"Automation in Construction"},{"key":"2022082710080515500_bib16","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1007\/s11069-021-05115-8","article-title":"Prediction of safety factors for slope stability: Comparison of machine learning techniques","volume":"111","author":"Mahmoodzadeh","year":"2022","journal-title":"Natural Hazards"},{"key":"2022082710080515500_bib22","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1109\/ICCVW.2017.107","article-title":"Image-based localization using hourglass networks","volume-title":"Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)","author":"Melekhov","year":"2017"},{"key":"2022082710080515500_bib38","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1007\/978-3-319-70353-4_57","article-title":"Relative camera pose estimation using convolutional neural networks","volume-title":"Proceedings of the International Conference on Advanced Concepts for Intelligent Vision Systems","author":"Melekhov","year":"2017"},{"key":"2022082710080515500_bib5","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","article-title":"ORB-SLAM: A versatile and accurate monocular SLAM system","volume":"31","author":"Mur-Artal","year":"2015","journal-title":"IEEE Transactions on Robotics"},{"key":"2022082710080515500_bib6","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","article-title":"ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras","volume":"33","author":"Mur-Artal","year":"2017","journal-title":"IEEE Transactions on Robotics"},{"key":"2022082710080515500_bib23","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.1109\/IROS.2017.8205957","article-title":"Deep regression for monocular camera-based 6-DoF global localization in outdoor environments","volume-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Naseer","year":"2017"},{"key":"2022082710080515500_bib42","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2022082710080515500_bib34","doi-asserted-by":"crossref","first-page":"4407","DOI":"10.1109\/LRA.2018.2869640","article-title":"VLocNet++: Deep multitask learning for semantic visual localization and odometry","volume":"3","author":"Radwan","year":"2018","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2022082710080515500_bib4","doi-asserted-by":"crossref","first-page":"2564","DOI":"10.1109\/ICCV.2011.6126544","article-title":"ORB: An efficient alternative to SIFT or SURF","volume-title":"Proceedings of the 2011 International Conference on Computer Vision","author":"Rublee","year":"2011"},{"key":"2022082710080515500_bib35","article-title":"Paying attention to activation maps in camera pose regression","volume-title":"arXiv preprint","author":"Shavit","year":"2021"},{"key":"2022082710080515500_bib36","doi-asserted-by":"crossref","first-page":"3186","DOI":"10.1109\/ICPR48806.2021.9412225","article-title":"Do we really need Scene-specific pose encoders?","volume-title":"Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR)","author":"Shavit","year":"2021"},{"key":"2022082710080515500_bib24","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv preprint","author":"Simonyan","year":"2014"},{"key":"2022082710080515500_bib21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CVPR.2015.7298594","article-title":"Going deeper with convolutions","volume-title":"Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Szegedy","year":"2015"},{"key":"2022082710080515500_bib33","doi-asserted-by":"crossref","first-page":"6939","DOI":"10.1109\/ICRA.2018.8462979","article-title":"Deep auxiliary learning for visual localization and odometry","volume-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)","author":"Valada","year":"2018"},{"key":"2022082710080515500_bib18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICECCT.2019.8869364","article-title":"Pneumonia detection using CNN based feature extraction","volume-title":"2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT)","author":"Varshni","year":"2019"},{"key":"2022082710080515500_bib25","first-page":"627","article-title":"Image-based localization using LSTMs for structured feature correlation","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"Walch","year":"2017"},{"article-title":"VisualSFM: A visual structure from motion system","year":"2011","author":"Wu","key":"2022082710080515500_bib7"},{"key":"2022082710080515500_bib11","first-page":"4588","article-title":"Monocular camera localization in prior LiDAR maps with 2D-3D line correspondences","volume-title":"Proceedings of the 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Yu","year":"2020"},{"key":"2022082710080515500_bib15","first-page":"1","article-title":"OLCN: An optimized low coupling network for small objects detection","volume":"19","author":"Yuan","year":"2021","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"article-title":"Posenet++: A CNN Framework for Online Pose Regression and Robot Re-Localization","year":"2018","author":"Zhang","key":"2022082710080515500_bib27"}],"container-title":["Journal of Computational Design and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcde\/advance-article-pdf\/doi\/10.1093\/jcde\/qwac066\/45084243\/qwac066.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/9\/4\/1482\/45596045\/qwac066.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/9\/4\/1482\/45596045\/qwac066.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,27]],"date-time":"2022-08-27T10:09:31Z","timestamp":1661594971000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/9\/4\/1482\/6650218"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,26]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,8,27]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwac066","relation":{},"ISSN":["2288-5048"],"issn-type":[{"type":"electronic","value":"2288-5048"}],"subject":[],"published-other":{"date-parts":[[2022,8]]},"published":{"date-parts":[[2022,7,26]]}}}