{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T08:44:35Z","timestamp":1748249075381},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T00:00:00Z","timestamp":1678233600000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>To mitigate the current COVID-19 pandemic, policy makers at the Greater London Authority, the regional governance body of London, UK, are reliant upon prompt, accurate and actionable estimations of lockdown and social distancing policy adherence. Transport for London, the local transportation department, reports they implemented over 700 interventions such as greater signage and expansion of pedestrian zoning at the height of the pandemic\u2019s first wave with our platform providing key data for those decisions. Large well-defined heterogeneous compositions of pedestrian footfall and physical proximity are difficult to acquire, yet necessary to monitor city-wide activity (busyness) and consequently discern actionable policy decisions. To meet this challenge, we leverage our existing large-scale data processing urban air quality machine learning infrastructure to process over 900 camera feeds in near real-time to generate new estimates of social distancing adherence, group detection and camera stability. In this work, we describe our development and deployment of a computer vision and machine learning pipeline. It provides near immediate sampling and contextualization of activity and physical distancing on the streets of London via live traffic camera feeds. We introduce a platform for inspecting, calibrating and improving upon existing methods, describe the active deployment on real-time feeds and provide analysis over an 18 month period.<\/jats:p>","DOI":"10.1093\/comjnl\/bxac160","type":"journal-article","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T12:43:05Z","timestamp":1678279385000},"page":"95-109","source":"Crossref","is-referenced-by-count":1,"title":["Near Real-Time Social Distance Estimation In London"],"prefix":"10.1093","volume":"67","author":[{"given":"James","family":"Walsh","sequence":"first","affiliation":[{"name":"The Alan Turing Institute; Departments of"}]},{"given":"Oluwafunmilola","family":"Kesa","sequence":"additional","affiliation":[{"name":"Computer Science"}]},{"given":"Andrew","family":"Wang","sequence":"additional","affiliation":[{"name":"Christ\u2019s College, University of Cambridge"}]},{"given":"Mihai","family":"Ilas","sequence":"additional","affiliation":[{"name":"Christ\u2019s College, University of Cambridge"}]},{"given":"Patrick","family":"O\u2019Hara","sequence":"additional","affiliation":[{"name":"Computer Science"}]},{"given":"Oscar","family":"Giles","sequence":"additional","affiliation":[{"name":"The Alan Turing Institute; Departments of"}]},{"given":"Neil","family":"Dhir","sequence":"additional","affiliation":[{"name":"The Alan Turing Institute; Departments of"},{"name":"Computer Science"}]},{"given":"Mark","family":"Girolami","sequence":"additional","affiliation":[{"name":"The Alan Turing Institute; Departments of"},{"name":"Department of Engineering, University of Cambridge"}]},{"given":"Theodoros","family":"Damoulas","sequence":"additional","affiliation":[{"name":"The Alan Turing Institute; Departments of"},{"name":"Computer Science"},{"name":"Statistics, University of Warwick"}]}],"member":"286","published-online":{"date-parts":[[2023,3,7]]},"reference":[{"key":"2024012011485251000_ref1","author":"GoogleTrends","year":"2021"},{"key":"2024012011485251000_ref2","volume-title":"Social Distancing Keyword in Google Books","author":"GoogleBooks","year":"2021"},{"key":"2024012011485251000_ref3","article-title":"Lockdown-type measures look effective against covid-19","volume":"370","author":"May","year":"2020","journal-title":"BMJ"},{"key":"2024012011485251000_ref4","volume-title":"Coronavirus (COVID-19) Mobility Report","author":"Authority","year":"2021"},{"key":"2024012011485251000_ref5","volume-title":"Open Government Licence","author":"HM Government","year":"2020"},{"key":"2024012011485251000_ref6","first-page":"1","volume-title":"Advances in Neural Information Processing Systems","author":"Hamelijnck","year":"2019"},{"key":"2024012011485251000_ref7","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1016\/j.trd.2012.06.008","article-title":"Congestion and emissions mitigation: A comparison of capacity, demand, and vehicle based strategies","volume":"17","author":"Bigazzi","year":"2012","journal-title":"Transportation Research Part D: Transport and Environment"},{"key":"2024012011485251000_ref8","volume-title":"Ethics Advisory Group","author":"The Alan Turing Institute","year":"2021"},{"key":"2024012011485251000_ref9","volume-title":"Kubernetes","author":"Cloud Native Computing Foundation","year":"2022"},{"key":"2024012011485251000_ref10","article-title":"Yolov4: Optimal speed and accuracy of object detection","volume-title":"arXiv preprint arXiv:2004.10934","author":"Bochkovskiy","year":"2020"},{"key":"2024012011485251000_ref11","author":"Redmon","year":"2022"},{"key":"2024012011485251000_ref12","author":"The PostgreSQL Global Development Group","year":"2022"},{"key":"2024012011485251000_ref13","volume-title":"Machine Learning in Public Health workshop, Neural Information Processing Systems","author":"Haycock","year":"2020"},{"key":"2024012011485251000_ref14","volume-title":"UK Government Department of Health and Social Care guided \u201cSupport Bubble\u201d","author":"Guidance","year":"2021"},{"key":"2024012011485251000_ref15","volume-title":"Elements of Photogrammetry (with Applications in GIS)","author":"Dewitt","year":"2000"},{"key":"2024012011485251000_ref16","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1016\/S0262-8856(03)00137-9","article-title":"Image registration methods: a survey","volume":"21","author":"Zitov\u00e1","year":"2003","journal-title":"Image and Vision Computing"},{"key":"2024012011485251000_ref17","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/BF00127813","article-title":"Using vanishing points for camera calibration","volume":"4","author":"Caprile","year":"1990","journal-title":"International Journal of Computer Vision"},{"key":"2024012011485251000_ref18","volume-title":"Three-dimensional computer vision: a geometric viewpoint","author":"Faugeras","year":"1993"},{"key":"2024012011485251000_ref19","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1109\/JRA.1987.1087109","article-title":"A versatile camera calibration technique for high-accuracy 3d machine vision metrology using off-the-shelf tv cameras and lenses","volume":"3","author":"Tsai","year":"1987","journal-title":"IEEE Journal on Robotics and Automation"},{"key":"2024012011485251000_ref20","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/TITS.2003.821213","article-title":"Dynamic camera calibration of roadside traffic management cameras for vehicle speed estimation","volume":"4","author":"Schoepflin","year":"2003","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"2024012011485251000_ref21","first-page":"42.1","volume-title":"Proceedings of the British Machine Vision Conference","author":"Dubska","year":"2014"},{"key":"2024012011485251000_ref22","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/3477.865171","article-title":"Lane detection by orientation and length discrimination. IEEE Trans. Syst., Man","volume":"30","author":"Lai","year":"2000","journal-title":"Cybern. B"},{"key":"2024012011485251000_ref23","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1109\/TSMCB.2006.872271","article-title":"Dynamic Calibration of Pan-Tilt-Zoom Cameras for Traffic Monitoring","volume":"36","author":"Song","year":"2006","journal-title":"IEEE Trans. Syst. Man Cybern. B Cybern."},{"key":"2024012011485251000_ref24","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1109\/CSIE.2009.763","volume-title":"2009 WRI World Congress on Computer Science and Information Engineering","author":"Dong","year":"2009"},{"key":"2024012011485251000_ref25","doi-asserted-by":"crossref","first-page":"2967","DOI":"10.1117\/1.1606458","article-title":"Camera calibration from road lane markings","volume":"42","author":"Fung","year":"2003","journal-title":"Optical Engineering"},{"key":"2024012011485251000_ref26","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1109\/CVPR.1998.698649","volume-title":"Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)","author":"Liebowitz","year":"1998"},{"key":"2024012011485251000_ref27","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1109\/IVS.2005.1505199","volume-title":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005","author":"Cathey","year":"2005"},{"key":"2024012011485251000_ref28","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-85729-327-5","volume-title":"Accurate Visual Metrology from Single and Multiple Uncalibrated Images","author":"Criminisi","year":"2001"},{"key":"2024012011485251000_ref29","volume-title":"Algorithms for estimating mean vehicle speed using uncalibrated traffic management cameras","author":"Schoepflin","year":"2003"},{"key":"2024012011485251000_ref30","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings","author":"Simonyan","year":"2015"},{"key":"2024012011485251000_ref31","doi-asserted-by":"crossref","first-page":"1395","DOI":"10.1109\/ICCV.2015.164","volume-title":"2015 IEEE International Conference on Computer Vision (ICCV)","author":"Xie","year":"2015"},{"key":"2024012011485251000_ref32","doi-asserted-by":"crossref","first-page":"5872","DOI":"10.1109\/CVPR.2017.622","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2017"},{"key":"2024012011485251000_ref33","volume-title":"Computer Vision","author":"Shapiro","year":"2001"},{"key":"2024012011485251000_ref34","first-page":"518","volume-title":"IEEE Transactions on Circuits and Systems for Video Technology","author":"Zhang","year":"2013"},{"key":"2024012011485251000_ref35","author":"Transport for London","year":"2020"},{"key":"2024012011485251000_ref36","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016, Cham","author":"Liu","year":"2016"},{"key":"2024012011485251000_ref37","author":"Redmon","year":"2018"},{"key":"2024012011485251000_ref38","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/CVPR.2016.91","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Redmon","year":"2016"},{"key":"2024012011485251000_ref39","first-page":"740","volume-title":"Computer Vision - ECCV 2014, Cham Lecture Notes in Computer Science","author":"Lin","year":"2014"},{"key":"2024012011485251000_ref40","first-page":"5129","volume-title":"IEEE Transactions on Image Processing","author":"Luo","year":"2018"},{"key":"2024012011485251000_ref41","doi-asserted-by":"crossref","first-page":"2366","DOI":"10.1109\/ICPR.2010.579","volume-title":"2010 20th International Conference on Pattern Recognition","author":"Hor\u00e9","year":"2010"},{"key":"2024012011485251000_ref42","author":"Burg","year":"2020"},{"key":"2024012011485251000_ref43","doi-asserted-by":"crossref","first-page":"1590","DOI":"10.1080\/01621459.2012.737745","article-title":"Optimal detection of changepoints with a linear computational cost","volume":"107","author":"Killick","year":"2012","journal-title":"J. Am. Stat. Assoc."},{"key":"2024012011485251000_ref44","volume-title":"An improved algorithm for finding the strongly connected components of a directed graph","author":"Pearce","year":"2005"},{"key":"2024012011485251000_ref45","author":"Sekachev","year":"2020"},{"key":"2024012011485251000_ref46","volume-title":"GLA COVID-19 Restrictions Timeseries","author":"Authority, T. G. L","year":"2021"},{"key":"2024012011485251000_ref47","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1080\/01621459.1979.10481038","article-title":"Robust locally weighted regression and smoothing scatterplots","volume":"74","author":"Cleveland","year":"1979","journal-title":"J. Am. Stat. Assoc."},{"key":"2024012011485251000_ref48","volume-title":"Helping London Navigate Lockdown Safely","author":"Lloyd","year":"2021"},{"key":"2024012011485251000_ref49","author":"Vryzakis","year":"2021"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/67\/1\/95\/56167720\/bxac160.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/67\/1\/95\/56167720\/bxac160.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,20]],"date-time":"2024-01-20T11:49:48Z","timestamp":1705751388000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/67\/1\/95\/7071574"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,7]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,3,7]]},"published-print":{"date-parts":[[2024,1,17]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxac160","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,1]]},"published":{"date-parts":[[2023,3,7]]}}}