{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:19:28Z","timestamp":1779383968328,"version":"3.53.1"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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","award":["62273282"],"award-info":[{"award-number":["62273282"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U25A20537"],"award-info":[{"award-number":["U25A20537"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113434","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T07:57:49Z","timestamp":1773129469000},"page":"113434","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FSO-VO: Visual odometry based on dense optical flow prediction and sequence optimization"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0868-9063","authenticated-orcid":false,"given":"Ganchao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8764-8335","authenticated-orcid":false,"given":"Sihang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1860-3275","authenticated-orcid":false,"given":"Yuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.patcog.2026.113434_bib0001","doi-asserted-by":"crossref","first-page":"2652","DOI":"10.1109\/TCYB.2018.2831900","article-title":"Odometry-vision-based ground vehicle motion estimation with SE (2)-constrained SE (3) poses","volume":"49","author":"Zheng","year":"2018","journal-title":"IEEE Trans. Cybern."},{"issue":"10","key":"10.1016\/j.patcog.2026.113434_bib0002","doi-asserted-by":"crossref","first-page":"10111","DOI":"10.1109\/TCYB.2021.3069806","article-title":"Relative pose estimation with a single affine correspondence","volume":"52","author":"Guan","year":"2021","journal-title":"IEEE Trans. Cybern."},{"issue":"5","key":"10.1016\/j.patcog.2026.113434_bib0003","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. Rob."},{"issue":"3","key":"10.1016\/j.patcog.2026.113434_bib0004","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1109\/TPAMI.2017.2658577","article-title":"Direct sparse odometry","volume":"40","author":"Engel","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113434_bib0005","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"},{"key":"10.1016\/j.patcog.2026.113434_bib0006","series-title":"European Conference on Computer Vision","first-page":"834","article-title":"LSD-SLAM: Large-scale direct monocular SLAM","author":"Engel","year":"2014"},{"issue":"5","key":"10.1016\/j.patcog.2026.113434_bib0007","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 Trans. Rob."},{"key":"10.1016\/j.patcog.2026.113434_bib0008","doi-asserted-by":"crossref","DOI":"10.1109\/TSMC.2024.3389012","article-title":"A tightly-Coupled and keyframe-Based visual-Inertial-Lidar odometry system for UGVs with adaptive sensor reliability evaluation","author":"Yin","year":"2024","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"10.1016\/j.patcog.2026.113434_bib0009","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"12179","article-title":"Vision transformers for dense prediction","author":"Ranftl","year":"2021"},{"key":"10.1016\/j.patcog.2026.113434_bib0010","article-title":"BEMN: Balanced bias enhanced multi-branch network for cross-view geo-localization","author":"Bi","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113434_bib0011","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume":"32","author":"Bian","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113434_bib0012","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"340","article-title":"Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction","author":"Zhan","year":"2018"},{"key":"10.1016\/j.patcog.2026.113434_bib0013","article-title":"Multi-Source temporal-Depth fusion for robust end-to-End visual odometry","author":"Zhang","year":"2026","journal-title":"Neural Netw."},{"key":"10.1016\/j.patcog.2026.113434_bib0014","article-title":"Enhancing visual inertial odometry with efficient dynamic perceptionnet and consistency improvement fusion","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113434_bib0015","series-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"4203","article-title":"Visual odometry revisited: what should be learnt?","author":"Zhan","year":"2020"},{"key":"10.1016\/j.patcog.2026.113434_bib0016","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.patcog.2026.113434_bib0017","unstructured":"S. Vijayanarasimhan, S. Ricco, C. Schmid, R. Sukthankar, K. Fragkiadaki, Sfm-net: Learning of structure and motion from video,(2017) arXiv: 1704.07804."},{"key":"10.1016\/j.patcog.2026.113434_bib0018","unstructured":"A.O. Fran\u00e7ani, M.R. Maximo, Transformer-based model for monocular visual odometry: a video understanding approach,(2023) arXiv: 2305.06121."},{"key":"10.1016\/j.patcog.2026.113434_bib0019","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.patcog.2026.113434_bib0020","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1983","article-title":"Geonet: unsupervised learning of dense depth, optical flow and camera pose","author":"Yin","year":"2018"},{"key":"10.1016\/j.patcog.2026.113434_bib0021","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2758","article-title":"Flownet: learning optical flow with convolutional networks","author":"Dosovitskiy","year":"2015"},{"key":"10.1016\/j.patcog.2026.113434_bib0022","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2462","article-title":"Flownet 2.0: evolution of optical flow estimation with deep networks","author":"Ilg","year":"2017"},{"key":"10.1016\/j.patcog.2026.113434_bib0023","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8981","article-title":"Liteflownet: a lightweight convolutional neural network for optical flow estimation","author":"Hui","year":"2018"},{"key":"10.1016\/j.patcog.2026.113434_bib0024","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16","first-page":"402","article-title":"Raft: recurrent all-pairs field transforms for optical flow","author":"Teed","year":"2020"},{"key":"10.1016\/j.patcog.2026.113434_bib0025","unstructured":"N. Eslami, F. Arefi, A.M. Mansourian, S. Kasaei, Rethinking RAFT for Efficient Optical Flow,(2024) arXiv: 2401.00833."},{"key":"10.1016\/j.patcog.2026.113434_bib0026","series-title":"2022 Latin American Robotics Symposium (LARS), 2022 Brazilian Symposium on Robotics (SBR), and 2022 Workshop on Robotics in Education (WRE)","first-page":"1","article-title":"Dense prediction transformer for scale estimation in monocular visual odometry","author":"Fran\u00e7ani","year":"2022"},{"key":"10.1016\/j.patcog.2026.113434_bib0027","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"10.1016\/j.patcog.2026.113434_bib0028","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.patcog.2026.113434_bib0029","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9772","article-title":"Learning to estimate hidden motions with global motion aggregation","author":"Jiang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113434_bib0030","article-title":"Beyond grids: learning graph representations for visual recognition","volume":"31","author":"Li","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113434_bib0031","unstructured":"T.N. Kipf, M. Welling, Semi-supervised classification with graph convolutional networks,(2016) arXiv: 1609.02907."},{"key":"10.1016\/j.patcog.2026.113434_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5754","article-title":"Iterative residual refinement for joint optical flow and occlusion estimation","author":"Hur","year":"2019"},{"issue":"6","key":"10.1016\/j.patcog.2026.113434_bib0033","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/358669.358692","article-title":"Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography","volume":"24","author":"Fischler","year":"1981","journal-title":"Commun. ACM"},{"key":"10.1016\/j.patcog.2026.113434_bib0034","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1023\/A:1008140928553","article-title":"The problem of degeneracy in structure and motion recovery from uncalibrated image sequences","volume":"32","author":"Torr","year":"1999","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113434_bib0035","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8934","article-title":"Pwc-net: cnns for optical flow using pyramid, warping, and cost volume","author":"Sun","year":"2018"},{"issue":"8","key":"10.1016\/j.patcog.2026.113434_bib0036","doi-asserted-by":"crossref","first-page":"2555","DOI":"10.1109\/TPAMI.2020.2976928","article-title":"A lightweight optical flow cnn-revisiting data fidelity and regularization","volume":"43","author":"Hui","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113434_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6278","article-title":"Maskflownet: Asymmetric feature matching with learnable occlusion mask","author":"Zhao","year":"2020"},{"key":"10.1016\/j.patcog.2026.113434_bib0038","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2462","article-title":"Flownet 2.0: Evolution of optical flow estimation with deep networks","author":"Ilg","year":"2017"},{"key":"10.1016\/j.patcog.2026.113434_bib0039","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16592","article-title":"Learning optical flow from a few matches","author":"Jiang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113434_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition","first-page":"17602","article-title":"Craft: Cross-attentional flow transformer for robust optical flow","author":"Sui","year":"2022"},{"key":"10.1016\/j.patcog.2026.113434_bib0041","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1890","article-title":"Learning optical flow with adaptive graph reasoning","volume":"36","author":"Luo","year":"2022"},{"key":"10.1016\/j.patcog.2026.113434_bib0042","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9521","article-title":"Explicit motion disentangling for efficient optical flow estimation","author":"Deng","year":"2023"},{"key":"10.1016\/j.patcog.2026.113434_bib0043","unstructured":"I. Loshchilov, F. Hutter, Decoupled weight decay regularization, arXiv: 1711.05101(2017)."},{"key":"10.1016\/j.patcog.2026.113434_bib0044","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4040","article-title":"A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation","author":"Mayer","year":"2016"},{"key":"10.1016\/j.patcog.2026.113434_bib0045","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8922","article-title":"LoFTR: Detector-free local feature matching with transformers","author":"Sun","year":"2021"},{"key":"10.1016\/j.patcog.2026.113434_bib0046","series-title":"European Conference on Computer Vision","first-page":"233","article-title":"Efficient deep visual and inertial odometry with adaptive visual modality selection","author":"Yang","year":"2022"},{"issue":"04","key":"10.1016\/j.patcog.2026.113434_bib0047","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1109\/34.88573","article-title":"Least-squares estimation of transformation parameters between two point patterns","volume":"13","author":"Umeyama","year":"1991","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"10.1016\/j.patcog.2026.113434_bib0048","series-title":"Conference on Robot Learning","first-page":"1761","article-title":"Tartanvo: A generalizable learning-based vo","author":"Wang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113434_bib0049","first-page":"39033","article-title":"Deep patch visual odometry","volume":"36","author":"Teed","year":"2023","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003997?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003997?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:54:27Z","timestamp":1779382467000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326003997"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":49,"alternative-id":["S0031320326003997"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113434","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FSO-VO: Visual odometry based on dense optical flow prediction and sequence optimization","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113434","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113434"}}