{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T13:02:59Z","timestamp":1780923779182,"version":"3.54.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.116256","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T15:38:51Z","timestamp":1779464331000},"page":"116256","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Geometry knowledge-embedded self-supervised deep monocular visual odometry for autonomous driving"],"prefix":"10.1016","volume":"347","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3547-3740","authenticated-orcid":false,"given":"Donglei","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3211-3219","authenticated-orcid":false,"given":"Wenjie","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0261-9782","authenticated-orcid":false,"given":"Yuqian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gui","family":"Gui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihua","family":"Gui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.knosys.2026.116256_b1","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TIV.2017.2749181","article-title":"Simultaneous localization and mapping: A survey of current trends in autonomous driving","volume":"2","author":"Bresson","year":"2017","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"6","key":"10.1016\/j.knosys.2026.116256_b2","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1109\/TRO.2016.2624754","article-title":"Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age","volume":"32","author":"Cadena","year":"2016","journal-title":"IEEE Trans. Robot."},{"issue":"12","key":"10.1016\/j.knosys.2026.116256_b3","doi-asserted-by":"crossref","first-page":"17000","DOI":"10.1109\/TNNLS.2023.3309809","article-title":"Deep learning for visual localization and mapping: A survey","volume":"35","author":"Chen","year":"2024","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116256_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2024.109127","article-title":"Towards explainable artificial intelligence in deep vision-based odometry","volume":"115","author":"Ghasemieh","year":"2024","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.knosys.2026.116256_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2024.119274","article-title":"Robust visual-based localization and mapping for underwater vehicles: A survey","volume":"312","author":"Ding","year":"2024","journal-title":"Ocean Eng."},{"issue":"1","key":"10.1016\/j.knosys.2026.116256_b6","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1109\/TCDS.2020.3038898","article-title":"Approaches, challenges, and applications for deep visual odometry: Toward complicated and emerging areas","volume":"14","author":"Wang","year":"2022","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"issue":"18","key":"10.1016\/j.knosys.2026.116256_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e37356","article-title":"Monocular visual SLAM, visual odometry, and structure from motion methods applied to 3D reconstruction: A comprehensive survey","volume":"10","author":"Herrera-Granda","year":"2024","journal-title":"Heliyon"},{"key":"10.1016\/j.knosys.2026.116256_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117734","article-title":"A survey of state-of-the-art on visual SLAM","volume":"205","author":"Abaspur Kazerouni","year":"2022","journal-title":"Expert Syst. Appl."},{"issue":"12","key":"10.1016\/j.knosys.2026.116256_b9","doi-asserted-by":"crossref","first-page":"14226","DOI":"10.1109\/TITS.2023.3298715","article-title":"Geometry-aware network for unsupervised learning of monocular camera\u2019s ego-motion","volume":"24","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.knosys.2026.116256_b10","series-title":"2017 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"2043","article-title":"DeepVO: Towards end-to-end visual odometry with deep recurrent convolutional neural networks","author":"Wang","year":"2017"},{"key":"10.1016\/j.knosys.2026.116256_b11","series-title":"DF-VO: What should be learnt for visual odometry?","author":"Zhan","year":"2021"},{"key":"10.1016\/j.knosys.2026.116256_b12","series-title":"DytanVO: Joint refinement of visual odometry and motion segmentation in dynamic environments","author":"Shen","year":"2023"},{"key":"10.1016\/j.knosys.2026.116256_b13","unstructured":"J.-W. Bian, Z. Li, N. Wang, H. Zhan, C. Shen, M.-M. Cheng, I. Reid, Unsupervised scale-consistent depth and ego-motion learning from monocular video, in: Proceedings of the 33rd International Conference on Neural Information Processing Systems, 2019, pp. 1\u201317."},{"key":"10.1016\/j.knosys.2026.116256_b14","doi-asserted-by":"crossref","unstructured":"S. Li, X. Wu, Y. Cao, H. Zha, Generalizing to the open world: Deep visual odometry with online adaptation, in: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 13179\u201313188.","DOI":"10.1109\/CVPR46437.2021.01298"},{"key":"10.1016\/j.knosys.2026.116256_b15","series-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"7286","article-title":"UnDeepVO: Monocular visual odometry through unsupervised deep learning","author":"Li","year":"2018"},{"key":"10.1016\/j.knosys.2026.116256_b16","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6612","article-title":"Unsupervised learning of depth and ego-motion from video","author":"Zhou","year":"2017"},{"key":"10.1016\/j.knosys.2026.116256_b17","series-title":"ORB-SfMLearner: ORB-Guided Self-supervised Visual Odometry with Selective Online Adaptation","author":"Jin","year":"2024"},{"key":"10.1016\/j.knosys.2026.116256_b18","series-title":"Understanding the Limitations of CNN-based Absolute Camera Pose Regression","author":"Sattler","year":"2019"},{"key":"10.1016\/j.knosys.2026.116256_b19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2023.3315416","article-title":"Pseudo-LiDAR for visual odometry","volume":"72","author":"Miao","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.knosys.2026.116256_b20","series-title":"2011 International Conference on Computer Vision","first-page":"2564","article-title":"ORB: An efficient alternative to SIFT or SURF","author":"Rublee","year":"2011"},{"key":"10.1016\/j.knosys.2026.116256_b21","doi-asserted-by":"crossref","first-page":"8034","DOI":"10.1109\/TASE.2026.3682733","article-title":"NVMS-SLAM: Normal vector-based multi-session LiDAR SLAM in indoor environments","volume":"23","author":"Ma","year":"2026","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"5","key":"10.1016\/j.knosys.2026.116256_b22","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 Trans. Robot."},{"key":"10.1016\/j.knosys.2026.116256_b23","series-title":"2011 IEEE Intelligent Vehicles Symposium","first-page":"963","article-title":"StereoScan: Dense 3d reconstruction in real-time","author":"Geiger","year":"2011"},{"key":"10.1016\/j.knosys.2026.116256_b24","series-title":"Direct Sparse Odometry","author":"Engel","year":"2016"},{"key":"10.1016\/j.knosys.2026.116256_b25","series-title":"2014 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"15","article-title":"SVO: Fast semi-direct monocular visual odometry","author":"Forster","year":"2014"},{"issue":"4","key":"10.1016\/j.knosys.2026.116256_b26","doi-asserted-by":"crossref","first-page":"7113","DOI":"10.1109\/LRA.2021.3097052","article-title":"DPLVO: Direct Point-Line Monocular Visual Odometry","volume":"6","author":"Zhou","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.knosys.2026.116256_b27","series-title":"EdgeVO: An Efficient and Accurate Edge-based Visual Odometry","author":"Zhao","year":"2023"},{"issue":"20","key":"10.1016\/j.knosys.2026.116256_b28","doi-asserted-by":"crossref","first-page":"8655","DOI":"10.3390\/s23208655","article-title":"A robust and integrated visual odometry framework exploiting the optical flow and feature point method","volume":"23","author":"Qiu","year":"2023","journal-title":"Sensors"},{"issue":"7","key":"10.1016\/j.knosys.2026.116256_b29","doi-asserted-by":"crossref","first-page":"2847","DOI":"10.1007\/s00371-022-02497-z","article-title":"Entanglement inspired approach ffor determining the preeminent arrangement of static cameras in a multi-view computer vision system","volume":"39","author":"Kumar","year":"2023","journal-title":"Vis. Comput."},{"key":"10.1016\/j.knosys.2026.116256_b30","series-title":"SelfOdom: Self-supervised egomotion and depth learning via bi-directional coarse-to-fine scale recovery","author":"Qu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116256_b31","series-title":"Self-supervised ego-motion estimation based on multi-layer fusion of RGB and inferred depth","author":"Jiang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116256_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113467","article-title":"IFDepth: Iterative fusion network for multi-frame self-supervised monocular depth estimation","volume":"318","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116256_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.116207","article-title":"SCFP-depth: Achieving robust self-supervised monocular depth estimation via static compensation and frequency-domain priors","volume":"346","author":"Yang","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116256_b34","first-page":"1","article-title":"Global-context-aware visual odometry system with epipolar-geometry-constrained loss function","volume":"73","author":"Ji","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.knosys.2026.116256_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112332","article-title":"SuPrNet: Super proxy for 4D occupancy forecasting","volume":"301","author":"Liang","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116256_b36","doi-asserted-by":"crossref","unstructured":"T. Shen, Z. Luo, L. Zhou, H. Zhang, L. Quan, T. Fang, Beyond photometric loss for self-supervised ego-motion estimation, in: Proceedings of the IEEE International Conference on Robotics and Automation, ICRA, 2019, pp. 6359\u20136365.","DOI":"10.1109\/ICRA.2019.8793479"},{"key":"10.1016\/j.knosys.2026.116256_b37","doi-asserted-by":"crossref","unstructured":"L. Tiwari, P. Ji, Q.-H. Tran, B. Zhuang, S. Anand, M. Chandraker, Pseudo RGB-D for self-improving monocular SLAM and depth prediction, in: Proceedings of the European Conference on Computer Vision, ECCV, 2020, pp. 437\u2013455.","DOI":"10.1007\/978-3-030-58621-8_26"},{"key":"10.1016\/j.knosys.2026.116256_b38","series-title":"Spatial transformer networks","author":"Jaderberg","year":"2016"},{"key":"10.1016\/j.knosys.2026.116256_b39","series-title":"Digging into self-supervised monocular depth estimation","author":"Godard","year":"2019"},{"issue":"4","key":"10.1016\/j.knosys.2026.116256_b40","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116256_b41","series-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3354","article-title":"Are we ready for autonomous driving? The KITTI vision benchmark suite","author":"Geiger","year":"2012"},{"issue":"1","key":"10.1016\/j.knosys.2026.116256_b42","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/0278364916679498","article-title":"1 year, 1000 km: The Oxford RobotCar dataset","volume":"36","author":"Maddern","year":"2017","journal-title":"Int. J. Robot. Res."},{"issue":"5","key":"10.1016\/j.knosys.2026.116256_b43","doi-asserted-by":"crossref","first-page":"4766","DOI":"10.1109\/LRA.2024.3384911","article-title":"SWformer-VO: A monocular visual odometry model based on swin transformer","volume":"9","author":"Wu","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.knosys.2026.116256_b44","series-title":"TartanVO: A Generalizable Learning-based VO","author":"Wang","year":"2020"},{"issue":"20","key":"10.1016\/j.knosys.2026.116256_b45","doi-asserted-by":"crossref","first-page":"39148","DOI":"10.1109\/JSEN.2025.3606150","article-title":"ARFF-VO: A self-supervised monocular visual odometry with adaptive region-based feature filtering in dynamic scenes","volume":"25","author":"Tong","year":"2025","journal-title":"IEEE Sensors J."},{"issue":"6","key":"10.1016\/j.knosys.2026.116256_b46","doi-asserted-by":"crossref","first-page":"8006","DOI":"10.1109\/TITS.2025.3559077","article-title":"Self-supervised visual odometry based on scene appearance-structure incremental fusion","volume":"26","author":"Fu","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"18","key":"10.1016\/j.knosys.2026.116256_b47","doi-asserted-by":"crossref","first-page":"8047","DOI":"10.1109\/JSEN.2019.2917936","article-title":"Stereo visual odometry based on motion decoupling and special feature screening for navigation of autonomous vehicles","volume":"19","author":"Ci","year":"2019","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.knosys.2026.116256_b48","series-title":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"4390","article-title":"F-LOAM : Fast LiDAR Odometry and Mapping","author":"Wang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116256_b49","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21276","article-title":"AutoMine: An unmanned mine dataset","author":"Li","year":"2022"},{"issue":"2","key":"10.1016\/j.knosys.2026.116256_b50","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":"Int. J. Comput. Vis."},{"issue":"7","key":"10.1016\/j.knosys.2026.116256_b51","first-page":"1281","article-title":"Fast explicit diffusion for accelerated features in nonlinear scale spaces","volume":"34","author":"Alcantarilla","year":"2011","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009822?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009822?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T12:16:43Z","timestamp":1780921003000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126009822"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":51,"alternative-id":["S0950705126009822"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116256","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Geometry knowledge-embedded self-supervised deep monocular visual odometry for autonomous driving","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116256","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116256"}}