{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:35:53Z","timestamp":1740184553622,"version":"3.37.3"},"reference-count":40,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T00:00:00Z","timestamp":1636329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T00:00:00Z","timestamp":1636329600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"LABEX LIFESENSES [ANR-10-LABX-65] within the Investissements d'Avenir program"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2021,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The optical flow in an event camera is estimated using measurements in the address event representation (AER). Each measurement consists of a pixel address and the time at which a change in the pixel value equalled a given fixed threshold. The measurements in a small region of the pixel array and within a given window in time are approximated by a probability distribution defined on a finite set. The distributions obtained in this way form a three dimensional family parameterized by the pixel addresses and by time. Each parameter value has an associated Fisher\u2013Rao matrix obtained from the Fisher\u2013Rao metric for the parameterized family of distributions. The optical flow vector at a given pixel and at a given time is obtained from the eigenvector of the associated Fisher\u2013Rao matrix with the least eigenvalue. The Fisher\u2013Rao algorithm for estimating optical flow is tested on eight datasets, of which six have ground truth optical flow. It is shown that the Fisher\u2013Rao algorithm performs well in comparison with two state of the art algorithms for estimating optical flow from AER measurements.<\/jats:p>","DOI":"10.1088\/2634-4386\/ac2bed","type":"journal-article","created":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T11:08:00Z","timestamp":1636715280000},"page":"024004","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Optical flow estimation using the Fisher\u2013Rao metric"],"prefix":"10.1088","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2113-9119","authenticated-orcid":false,"given":"Stephen J","family":"Maybank","sequence":"first","affiliation":[]},{"given":"Sio-Hoi","family":"Ieng","sequence":"additional","affiliation":[]},{"given":"Davide","family":"Migliore","sequence":"additional","affiliation":[]},{"given":"Ryad","family":"Benosman","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2021,11,8]]},"reference":[{"key":"nceac2bedbib1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco_a_00703","article-title":"What can neuromorphic event-driven precise timing add to spike-based pattern recognition?","volume":"27","author":"Akolkar","year":"2015","journal-title":"Neural Comput."},{"year":"1985","author":"Amari","key":"nceac2bedbib2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-5056-2"},{"key":"nceac2bedbib3","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.102","article-title":"Simultaneous optical flow and intensity estimation from an event camera","author":"Bardow","year":"2016"},{"key":"nceac2bedbib4","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/jproc.2014.2347207","article-title":"Contour motion estimation for asynchronous event-driven cameras","volume":"102","author":"Barranco","year":"2014","journal-title":"Proc. IEEE"},{"key":"nceac2bedbib5","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3389\/fnins.2016.00049","article-title":"A dataset for visual navigation with neuromorphic methods","volume":"10","author":"Barranco","year":"2016","journal-title":"Front. Neurosci."},{"key":"nceac2bedbib6","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.neunet.2011.11.001","article-title":"Asynchronous frameless event-based optical flow","volume":"27","author":"Benosman","year":"2012","journal-title":"Neural Netw."},{"key":"nceac2bedbib7","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1109\/tnnls.2013.2273537","article-title":"Event-based visual flow","volume":"25","author":"Benosman","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learning Syst."},{"key":"nceac2bedbib8","first-page":"C186","article-title":"240 \u00d7 180 10 mW 12 us latency sparse-output vision sensor for mobile applications","author":"Berner","year":"2013"},{"key":"nceac2bedbib9","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1109\/82.842110","article-title":"Point-to-point\u00a0connectivity between neuromorphic chips using address events","volume":"47","author":"Boahen","year":"2000","journal-title":"IEEE Trans. Circuits Syst. II"},{"article-title":"Camera calibration toolbox for Matlab","year":"2015","author":"Bouguet","key":"nceac2bedbib10"},{"key":"nceac2bedbib11","doi-asserted-by":"publisher","first-page":"137","DOI":"10.3389\/fnins.2015.00137","article-title":"On event-based optical flow detection","volume":"9","author":"Brosch","year":"2015","journal-title":"Front. Neurosci."},{"key":"nceac2bedbib12","first-page":"p 2014","article-title":"On event-based motion detection and integration","author":"Brosch","year":"2015"},{"key":"nceac2bedbib13","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.neunet.2013.03.006","article-title":"Asynchronous event-based 3D reconstruction from neuromorphic retinas","volume":"45","author":"Carneiro","year":"2013","journal-title":"Neural Netw."},{"edition":"2nd edn","year":"2006","author":"Cover","key":"nceac2bedbib14"},{"key":"nceac2bedbib15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2015.02.008","article-title":"Optical flow modeling and computation: a survey","volume":"134","author":"Fortun","year":"2015","journal-title":"Comput. Vis. Image Understand."},{"key":"nceac2bedbib16","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00407","article-title":"A unifying contrast maximization framework for event cameras, with applications to motion, depth, and optical flow estimation","author":"Gallego","year":"2018"},{"article-title":"Event-based vision: a survey","year":"2019","author":"Gallego","key":"nceac2bedbib17"},{"key":"nceac2bedbib18","first-page":"5632","article-title":"End-to-end learning of representations for asynchronous event-based data","author":"Gehrig","year":"2019"},{"article-title":"Spatiotemporal filtering for event-based action recognition","year":"2019a","author":"Ghosh","key":"nceac2bedbib19"},{"article-title":"Spatiotemporal feature learning for event-based vision","year":"2019b","author":"Ghosh","key":"nceac2bedbib20"},{"key":"nceac2bedbib21","doi-asserted-by":"publisher","first-page":"2338","DOI":"10.1109\/tpami.2014.2327975","article-title":"Bin ratio-based histogram distances and their application to image classification","volume":"36","author":"Weiming Hu","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"nceac2bedbib22","doi-asserted-by":"publisher","first-page":"596","DOI":"10.3389\/fnins.2016.00596","article-title":"Event-based 3D motion flow estimation using 4D spatio temporal subspaces properties","volume":"10","author":"Ieng","year":"2017","journal-title":"Front. Neurosci."},{"key":"nceac2bedbib23","doi-asserted-by":"crossref","DOI":"10.1109\/AVSS.2006.5","article-title":"A comparison on histogram based image matching methods","author":"Jia","year":"2006"},{"key":"nceac2bedbib24","first-page":"674","article-title":"Event-based stereo matching approaches for frameless address event stereo data","volume":"vol 6938","author":"Kogler","year":"2011"},{"year":"1959","author":"Kullback","key":"nceac2bedbib25"},{"key":"nceac2bedbib26","doi-asserted-by":"publisher","first-page":"1710","DOI":"10.1109\/TNNLS 2014.2352401","article-title":"Asynchronous event-based multikernel algorithm for high-speed visual features tracking","volume":"26","author":"Lagorce","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learning Syst."},{"key":"nceac2bedbib27","doi-asserted-by":"crossref","DOI":"10.1109\/ARVLSI.1995.515618","article-title":"A multi-sender asynchronous extension to the AER protocol","author":"Lazzaro","year":"1995"},{"article-title":"Adaptive time-slice block-matching optical flow algorithm for dynamic vision sensors","year":"2018","author":"Liu","key":"nceac2bedbib28"},{"article-title":"VLSI analogs of neuronal visual processing: a synthesis of form and function","year":"1992","author":"Mahowald","key":"nceac2bedbib29"},{"year":"2017","key":"nceac2bedbib30","article-title":"OptiTrack documentation wiki"},{"key":"nceac2bedbib31","doi-asserted-by":"publisher","first-page":"2706","DOI":"10.1109\/tpami.2013.71","article-title":"Mapping from frame-driven to frame-free event-driven vision systems by low-rate rate coding and coincidence processing-application to feed forward ConvNets","volume":"35","author":"Perez-Carrasco","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"nceac2bedbib32","doi-asserted-by":"crossref","DOI":"10.1109\/ISCAS.2010.5537265","article-title":"Live demonstration: asynchronous tie-based image sensor (ATIS) camera with full-custom AE processor","author":"Posch","year":"2010"},{"key":"nceac2bedbib33","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1109\/tnnls.2011.2180025","article-title":"Asynchronous event-based binocular stereo matching","volume":"23","author":"Rogister","year":"2011","journal-title":"IEEE Trans. Neural Netw. Learning Syst."},{"key":"nceac2bedbib34","doi-asserted-by":"publisher","first-page":"176","DOI":"10.3389\/fnins.2016.00176","article-title":"Evaluation of event-based algorithms for optical flow with ground-truth from inertial measurement sensor","volume":"10","author":"Rueckauer","year":"2016","journal-title":"Front. Neurosci."},{"key":"nceac2bedbib35","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1016\/j.patcog.2006.08.012","article-title":"Image registration by local histogram matching","volume":"40","author":"Shen","year":"2007","journal-title":"Pattern Recognit."},{"year":"2011","author":"Szeliski","key":"nceac2bedbib36"},{"year":"2011","author":"Wedel","key":"nceac2bedbib37"},{"key":"nceac2bedbib38","doi-asserted-by":"publisher","first-page":"2032","DOI":"10.1109\/lra.2018.2800793","article-title":"The multivehicle stereo event camera dataset: an event camera dataset for 3D perception","volume":"3","author":"Zhu","year":"2018a","journal-title":"IEEE Robot. Autom. Lett."},{"key":"nceac2bedbib39","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2018.XIV.062","article-title":"EV-flownet: self-supervised optical flow estimation for event based cameras","author":"Zhu","year":"2018b"},{"key":"nceac2bedbib40","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00108","article-title":"Unsupervised event-based learning of optical flow, depth, and egomotion","author":"Zhu","year":"2019"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac2bed","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac2bed\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac2bed\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac2bed\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T11:08:06Z","timestamp":1636715286000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac2bed"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,8]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,11,8]]},"published-print":{"date-parts":[[2021,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ac2bed","relation":{},"ISSN":["2634-4386"],"issn-type":[{"type":"electronic","value":"2634-4386"}],"subject":[],"published":{"date-parts":[[2021,11,8]]},"assertion":[{"value":"Optical flow estimation using the Fisher\u2013Rao metric","name":"article_title","label":"Article Title"},{"value":"Neuromorphic Computing and Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2021-02-09","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-09-30","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-11-08","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}