{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T11:14:37Z","timestamp":1769339677595,"version":"3.49.0"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":1388,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/3.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Optical flow is a key method used for quantitative motion estimation of biological structures in light microscopy. It has also been used as a key module in segmentation and tracking systems and is considered a mature technology in the field of computer vision. However, most of the research focused on 2D natural images, which are small in size and rich in edges and texture information. In contrast, 3D time-lapse recordings of biological specimens comprise up to several terabytes of image data and often exhibit complex object dynamics as well as blurring due to the point-spread-function of the microscope. Thus, new approaches to optical flow are required to improve performance for such data.<\/jats:p>\n               <jats:p>Results: We solve optical flow in large 3D time-lapse microscopy datasets by defining a Markov random field (MRF) over super-voxels in the foreground and applying motion smoothness constraints between super-voxels instead of voxel-wise. This model is tailored to the specific characteristics of light microscopy datasets: super-voxels help registration in textureless areas, the MRF over super-voxels efficiently propagates motion information between neighboring cells and the background subtraction and super-voxels reduce the dimensionality of the problem by an order of magnitude. We validate our approach on large 3D time-lapse datasets of Drosophila and zebrafish development by analyzing cell motion patterns. We show that our approach is, on average, 10 \u00d7 faster than commonly used optical flow implementations in the Insight Tool-Kit (ITK) and reduces the average flow end point error by 50% in regions with complex dynamic processes, such as cell divisions.<\/jats:p>\n               <jats:p>Availability: Source code freely available in the Software section at http:\/\/janelia.org\/lab\/keller-lab.<\/jats:p>\n               <jats:p>Contact: \u00a0amatf@janelia.hhmi.org or kellerp@janelia.hhmi.org<\/jats:p>\n               <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/bts706","type":"journal-article","created":{"date-parts":[[2012,12,16]],"date-time":"2012-12-16T01:19:48Z","timestamp":1355620788000},"page":"373-380","source":"Crossref","is-referenced-by-count":48,"title":["Fast and robust optical flow for time-lapse microscopy using super-voxels"],"prefix":"10.1093","volume":"29","author":[{"given":"Fernando","family":"Amat","sequence":"first","affiliation":[{"name":"1 Howard Hughes Medical Institute, Janelia Farm Research Campus, Ashburn, VA 20147, USA and 2Max Planck Institute of Molecular Cell Biology and Genetics, 01307 Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugene W.","family":"Myers","sequence":"additional","affiliation":[{"name":"1 Howard Hughes Medical Institute, Janelia Farm Research Campus, Ashburn, VA 20147, USA and 2Max Planck Institute of Molecular Cell Biology and Genetics, 01307 Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philipp J.","family":"Keller","sequence":"additional","affiliation":[{"name":"1 Howard Hughes Medical Institute, Janelia Farm Research Campus, Ashburn, VA 20147, USA and 2Max Planck Institute of Molecular Cell Biology and Genetics, 01307 Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2012,12,14]]},"reference":[{"key":"2023012810233620300_bts706-B1","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1109\/TMI.2002.1000254","article-title":"Computation and visualization of three-dimensional soft tissue motion in the orbit","volume":"21","author":"Abramoff","year":"2002","journal-title":"IEEE Trans. Med. Imaging"},{"key":"2023012810233620300_bts706-B2","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","article-title":"SLIC superpixels compared to state-of-the-art superpixel methods","volume":"34","author":"Achanta","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2023012810233620300_bts706-B3","first-page":"100","article-title":"Occlusion detection and motion estimation with convex optimization","volume-title":"NIPS'10","author":"Ayvaci","year":"2010"},{"key":"2023012810233620300_bts706-B4","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/s11263-010-0390-2","article-title":"A database and evaluation methodology for optical flow","volume":"92","author":"Baker","year":"2011","journal-title":"Int. J. Comput. Vis."},{"key":"2023012810233620300_bts706-B5","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1006\/cviu.1996.0006","article-title":"The robust estimation of multiple motions: parametric and piecewise-smooth flow fields","volume":"63","author":"Black","year":"1996","journal-title":"Comput. Vis. Image Underst."},{"key":"2023012810233620300_bts706-B6","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TPAMI.2010.143","article-title":"Large displacement optical flow: descriptor matching in variational motion estimation","volume":"33","author":"Brox","year":"2011","journal-title":"IEEE Trans. PAMI"},{"key":"2023012810233620300_bts706-B7","first-page":"211","article-title":"Lucas\/Kanade meets Horn\/Schunck: combining local and global optic flow methods","volume":"61","author":"Bruhn","year":"2005","journal-title":"Int. J. Comupt. Vis."},{"key":"2023012810233620300_bts706-B8","doi-asserted-by":"crossref","first-page":"2520","DOI":"10.1007\/s10439-010-0005-7","article-title":"Mapping the spatiotemporal dynamics of calcium signaling in cellular neural networks using optical flow","volume":"38","author":"Buibas","year":"2010","journal-title":"Ann. Biomed. Eng."},{"key":"2023012810233620300_bts706-B9","doi-asserted-by":"crossref","first-page":"1190","DOI":"10.1137\/0916069","article-title":"A limited memory algorithm for bound constrained optimization","volume":"16","author":"Byrd","year":"1994","journal-title":"SIAM J. Sci. Comput."},{"key":"2023012810233620300_bts706-B10","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1007\/s00138-011-0362-8","article-title":"Performance of optical flow techniques for motion analysis of fluorescent point signals in confocal microscopy","volume":"23","author":"Delpiano","year":"2011","journal-title":"Mach. Vis. Appl."},{"key":"2023012810233620300_bts706-B11","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.laa.2003.10.021","article-title":"A unified approach to fast image registration and a new curvature based registration technique","volume":"380","author":"Fischer","year":"2004","journal-title":"Linear Algebra Appl."},{"key":"2023012810233620300_bts706-B12","first-page":"1","article-title":"Guiding optical flow estimation using superpixels","volume-title":"International Conference on Digital Signal Processing","author":"Gkamas","year":"2011"},{"key":"2023012810233620300_bts706-B13","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1016\/j.media.2008.03.006","article-title":"Dense image registration through MRFs and efficient linear programming","volume":"12","author":"Glocker","year":"2008","journal-title":"Med. Image Anal."},{"key":"2023012810233620300_bts706-B14","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","article-title":"Determining optical flow","volume":"17","author":"Horn","year":"1981","journal-title":"Aritifical Intell."},{"key":"2023012810233620300_bts706-B15","doi-asserted-by":"crossref","DOI":"10.1002\/0471725250","volume-title":"Robust Statistics","author":"Huber","year":"1981","edition":"1st"},{"key":"2023012810233620300_bts706-B16","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1109\/TMI.2010.2089384","article-title":"Automated mitosis detection of stem cell populations in Phase-Contrast microscopy images","volume":"30","author":"Huh","year":"2011","journal-title":"IEEE Trans. Med. Imaging"},{"key":"2023012810233620300_bts706-B17","volume-title":"The ITK Software Guide: The Insight Segmentation and Registration Toolkit","author":"Ibanez","year":"2003"},{"key":"2023012810233620300_bts706-B18","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1126\/science.1162493","article-title":"Reconstruction of zebrafish early embryonic development by scanned light sheet microscopy","volume":"322","author":"Keller","year":"2008","journal-title":"Science"},{"key":"2023012810233620300_bts706-B19","first-page":"1075","article-title":"Detection of deformable objects in 3D images using Markov-Chain monte carlo and spherical harmonics","volume-title":"MICCAI","author":"Khairy","year":"2008"},{"key":"2023012810233620300_bts706-B20","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1186\/1471-2121-8-40","article-title":"3D cell nuclei segmentation based on gradient flow tracking","volume":"8","author":"Li","year":"2007","journal-title":"BMC Cell Biol."},{"key":"2023012810233620300_bts706-B21","first-page":"1","article-title":"Numerical estimates for the huber M-Estimator problem","volume":"8","author":"Li","year":"1995","journal-title":"Approximation Theory"},{"key":"2023012810233620300_bts706-B22","first-page":"28","article-title":"SIFT flow: dense correspondence across different scenes","volume-title":"ECCV","author":"Liu","year":"2008"},{"key":"2023012810233620300_bts706-B23","article-title":"Evaluation of four 3d non rigid registration methods applied to early zebrafish development sequences","volume-title":"MIAAB MICCAI","author":"Lombardot","year":"2008"},{"key":"2023012810233620300_bts706-B24","doi-asserted-by":"crossref","first-page":"1557","DOI":"10.1109\/ISBI.2011.5872698","article-title":"Deltr: digital embryo lineage tree reconstructor","volume-title":"2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","author":"Lou","year":"2011"},{"key":"2023012810233620300_bts706-B25","first-page":"674","article-title":"An iterative image registration technique with an application to stereo vision","volume-title":"IJCAI","author":"Lucas","year":"1981"},{"key":"2023012810233620300_bts706-B26","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.1126\/science.1167094","article-title":"Dynamic analyses of drosophila gastrulation provide insights into collective cell migration","volume":"322","author":"McMahon","year":"2008","journal-title":"Science"},{"key":"2023012810233620300_bts706-B27","first-page":"51","article-title":"Optical flow estimation: advances and comparisons","volume-title":"ECCV","author":"Otte","year":"1994"},{"key":"2023012810233620300_bts706-B28","first-page":"1939","article-title":"Towards dense motion estimation in light and electron microscopy","volume-title":"ISBI","author":"Pizarro","year":"2011"},{"key":"2023012810233620300_bts706-B29","first-page":"511","article-title":"A duality based algorithm for TV-L1-optical-flow image registration","volume":"10 (Pt. 2)","author":"Pock","year":"2007","journal-title":"MICCAI"},{"key":"2023012810233620300_bts706-B30","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1038\/nmeth0610-418","article-title":"Software for bead-based registration of selective plane illumination microscopy data","volume":"7","author":"Preibisch","year":"2010","journal-title":"Nat. Methods"},{"key":"2023012810233620300_bts706-B31","first-page":"1093","article-title":"MRF modeling for optical flow computation from multi-structure objects","volume-title":"ICIP","author":"Prinet","year":"2006"},{"key":"2023012810233620300_bts706-B32","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1007\/s00138-009-0207-x","article-title":"Estimating the motion of plant root cells from in vivo confocal laser scanning microscopy images","volume":"21","author":"Roberts","year":"2010","journal-title":"Mach. Vis. Appl."},{"key":"2023012810233620300_bts706-B33","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1093\/bioinformatics\/btr609","article-title":"Wavelet-based image fusion in multi-view three-dimensional microscopy","volume":"28","author":"Rubio-Guivernau","year":"2012","journal-title":"Bioinformatics"},{"key":"2023012810233620300_bts706-B34","first-page":"230","article-title":"Ilastik: interactive learning and segmentation toolkit","volume-title":"ISBI","author":"Sommer","year":"2011"},{"key":"2023012810233620300_bts706-B35","first-page":"83","article-title":"Learning optical flow","volume-title":"ECCV","author":"Sun","year":"2008"},{"key":"2023012810233620300_bts706-B36","first-page":"2432","article-title":"Secrets of optical flow estimation and their principles","volume-title":"CVPR","author":"Sun","year":"2010"},{"key":"2023012810233620300_bts706-B37","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/S1361-8415(98)80022-4","article-title":"Image matching as a diffusion process: an analogy with maxwell\u2019s demons","volume":"2","author":"Thirion","year":"1998","journal-title":"Med. Image Anal."},{"key":"2023012810233620300_bts706-B38","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1038\/nmeth.2062","article-title":"Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy","volume":"9","author":"Tomer","year":"2012","journal-title":"Nat. Methods"},{"key":"2023012810233620300_bts706-B39","doi-asserted-by":"crossref","DOI":"10.5244\/C.23.108","article-title":"Anisotropic Huber-L1 optical flow","volume-title":"BMVC","author":"Werlberger","year":"2009"},{"key":"2023012810233620300_bts706-B40","first-page":"671","article-title":"A segmentation based variational model for accurate optical flow estimation","volume-title":"ECCV","author":"Xu","year":"2008"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/3\/373\/48897613\/bioinformatics_29_3_373.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/3\/373\/48897613\/bioinformatics_29_3_373.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T11:53:06Z","timestamp":1674906786000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/29\/3\/373\/257856"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,12,14]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,2,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bts706","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2013,2,1]]},"published":{"date-parts":[[2012,12,14]]}}}