Multimodal Anomaly Detection for Urban Safety: A Real-World Implementation in Large-Scale Surveillance Systems

Multimodal Anomaly Detection for Urban Safety: A Real-World Implementation in Large-Scale Surveillance Systems | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Multimodal Anomaly Detection for Urban Safety: A Real-World Implementation in Large-Scale Surveillance Systems Matthew R. Collins, Jiawei Zhang, Samuel D. Fraser, Emily K. Robinson This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7862447/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Effectively identifying abnormal events in urban environments requires the fusion of diverse data modalities, including video, audio, and environmental sensors. This paper presents a neural network-based framework for real-time multimodal anomaly detection deployed in a live metropolitan scenario. Using a combined CNN-LSTM structure and attention-based feature alignment, the system integrates heterogeneous inputs to classify anomalies across 57 event types. Field deployment across 28 surveillance zones demonstrated a detection precision of 93.4% and average processing latency of 0.89 seconds per frame group. The results validate the feasibility and robustness of deploying neural models for large-scale, cross-modal urban safety tasks. Medical Informatics Environmental Engineering multimodal anomaly detection smart surveillance real-time monitoring urban safety neural network fusion deep learning Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7862447","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":529729733,"identity":"6645446d-a495-48e0-9e25-063be0d6c6af","order_by":0,"name":"Matthew R. Collins","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIiWNgGAWjYLCCBAYJBgb2xsYHQDYPH3FaEoBaeA4fNgBpYSPWGgYGCbc0CRCboBb5GbnHJB7+sMiTj+Axq/yaYyfDxsD88NENPFoMbuQlGwAdVmx4u8fstuy2ZKDD2IyNc/BpkcgxfADUkrhxzhmz25LbmIFaeNik8WmRn5FjcACsZUaOWbHktnrCWhhuQG2ZL5GWxvhx22HCWgzOvDE2SEiTSNwADGRpxm3HediYCfhFvj3HTPKHTV3i/PbGxo8/t1Xb87M3P3yM12Fw6w4wMDDzgFjMxCgHW9fAwMD4g1jVo2AUjIJRMKIAAFJNRrMKAm1ZAAAAAElFTkSuQmCC","orcid":"","institution":"Department of Computer Science, University of Toronto, Toronto, ON M5S 2E4, [email protected]","correspondingAuthor":true,"prefix":"","firstName":"Matthew","middleName":"R.","lastName":"Collins","suffix":""},{"id":529729734,"identity":"b0abce2e-8a47-46c3-b1b5-64add338efc1","order_by":1,"name":"Jiawei Zhang","email":"","orcid":"","institution":"School of Computer Science, McGill University, Montreal, QC H3A 0E9, Canada","correspondingAuthor":false,"prefix":"","firstName":"Jiawei","middleName":"","lastName":"Zhang","suffix":""},{"id":529729735,"identity":"4f68d920-c0f5-4412-8ad1-2dec015d2da2","order_by":2,"name":"Samuel D. Fraser","email":"","orcid":"","institution":"Department of Computer Science, University of Toronto, Toronto, ON M5S 2E4, Canada","correspondingAuthor":false,"prefix":"","firstName":"Samuel","middleName":"D.","lastName":"Fraser","suffix":""},{"id":529729736,"identity":"ab60873b-8359-43a4-842e-f0eb4f6bbfde","order_by":3,"name":"Emily K. Robinson","email":"","orcid":"","institution":"School of Computer Science, McGill University, Montreal, QC H3A 0E9, Canada","correspondingAuthor":false,"prefix":"","firstName":"Emily","middleName":"K.","lastName":"Robinson","suffix":""}],"badges":[],"createdAt":"2025-10-15 01:01:33","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7862447/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7862447/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93641205,"identity":"baa43cb8-3cdb-4b8a-95bd-dc23c3f187f8","added_by":"auto","created_at":"2025-10-16 02:47:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":461816,"visible":true,"origin":"","legend":"","description":"","filename":"9.2504YaoMultimodalAnomalyDetectionforUrbanSafetyARealWorldImplementationinLargeScaleSurveillanceSystems.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7862447/v1_covered_affdb2a4-8b36-4526-810f-dac2ff006eb8.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eMultimodal Anomaly Detection for Urban Safety: A Real-World Implementation in Large-Scale Surveillance Systems\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"multimodal anomaly detection, smart surveillance, real-time monitoring, urban safety, neural network fusion, deep learning","lastPublishedDoi":"10.21203/rs.3.rs-7862447/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7862447/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEffectively identifying abnormal events in urban environments requires the fusion of diverse data modalities, including video, audio, and environmental sensors. This paper presents a neural network-based framework for real-time multimodal anomaly detection deployed in a live metropolitan scenario. Using a combined CNN-LSTM structure and attention-based feature alignment, the system integrates heterogeneous inputs to classify anomalies across 57 event types. Field deployment across 28 surveillance zones demonstrated a detection precision of 93.4% and average processing latency of 0.89 seconds per frame group. The results validate the feasibility and robustness of deploying neural models for large-scale, cross-modal urban safety tasks.\u003c/p\u003e","manuscriptTitle":"Multimodal Anomaly Detection for Urban Safety: A Real-World Implementation in Large-Scale Surveillance Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-16 02:39:52","doi":"10.21203/rs.3.rs-7862447/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6f7b2703-9d1b-4c8d-b12e-1725890ad419","owner":[],"postedDate":"October 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56306220,"name":"Medical Informatics"},{"id":56306221,"name":"Environmental Engineering"}],"tags":[],"updatedAt":"2025-10-16T02:39:52+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-16 02:39:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7862447","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7862447","identity":"rs-7862447","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}