Low-complexity pedestrian intent prediction using contextual stacked ensemble learning

Low-complexity pedestrian intent prediction using contextual stacked ensemble learning | 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 Article Low-complexity pedestrian intent prediction using contextual stacked ensemble learning Chia-Yen Chiang, Yasmin Fathy, Gregory Slabaugh, Mona Jaber This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8639560/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 15 You are reading this latest preprint version Abstract Walking, as a form of active and sustainable mobility, plays a critical role in future smart transportation systems. Accurate prediction of pedestrian crossing intentions is essential for preventing collisions, particularly with the increasing deployment of autonomous vehicles.Existing approaches to near-miss prevention typically rely on computationally intensive computer vision and deep learning techniques. In contrast, this work proposes CSE, a lightweight contextual stacked ensemble-learning framework to efficiently predict pedestrian crossing intent. Pedestrians are first detected and their visual representation is compressed through skeletonization, and complementary pose, trajectory, and contextual cues are fused using a stacked ensemble model.Experimental results on multiple datasets demonstrate that the proposed approach achieves performance comparable to state-of-the-art pedestrian intent prediction methods while reducing computational complexity by at least $25$ times. This reduction translates directly into a $25\times$ decrease in inference time, enabling deployment on resource-constrained edge devices without compromising accuracy and while avoiding the latency associated with cloud-based processing. Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 13 Mar, 2026 Reviewers agreed at journal 01 Mar, 2026 Reviews received at journal 26 Feb, 2026 Reviews received at journal 26 Feb, 2026 Reviews received at journal 24 Feb, 2026 Reviewers agreed at journal 22 Feb, 2026 Reviewers agreed at journal 31 Jan, 2026 Reviewers agreed at journal 30 Jan, 2026 Reviews received at journal 30 Jan, 2026 Reviewers agreed at journal 30 Jan, 2026 Reviewers invited by journal 27 Jan, 2026 Editor invited by journal 27 Jan, 2026 Editor assigned by journal 22 Jan, 2026 Submission checks completed at journal 22 Jan, 2026 First submitted to journal 19 Jan, 2026 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-8639560","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":581898398,"identity":"df35df1c-359a-4e47-bc38-3691309e38cf","order_by":0,"name":"Chia-Yen Chiang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIiWNgGAWjYHACNoYEIMkPYj6AChCnRbIBSCQQrQUEDA4Qq4W/gfnZgwc1d+w2H89Ok0hgsJNnkEhLwKtF4gCbuUHCsWfJ28683QbUkmzYIJF2AK8WAwYeNokEtsPJZjdyQVqYExgk0huI0PLvcLLxDLCWeiK1JLYdtjOQAGs5DNRCwGESh9nMJBL7DidInHm72SLB4LhhG8+zBLxa+Nubn0n++HbYnr89d+ONDxXV8vzsaQZ4tTAwQ6jEBnCkGBATkVBgD4vHUTAKRsEoGAUYAADQzT/drOD0igAAAABJRU5ErkJggg==","orcid":"","institution":"Queen Mary University of London","correspondingAuthor":true,"prefix":"","firstName":"Chia-Yen","middleName":"","lastName":"Chiang","suffix":""},{"id":581898399,"identity":"56924829-36bc-4e70-88df-4622a8510720","order_by":1,"name":"Yasmin Fathy","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Yasmin","middleName":"","lastName":"Fathy","suffix":""},{"id":581898400,"identity":"a9db492c-1284-416d-acdc-6b4aeea00578","order_by":2,"name":"Gregory Slabaugh","email":"","orcid":"","institution":"Queen Mary University of London","correspondingAuthor":false,"prefix":"","firstName":"Gregory","middleName":"","lastName":"Slabaugh","suffix":""},{"id":581898401,"identity":"223f1b85-4996-40e6-8d05-6638f08ff799","order_by":3,"name":"Mona Jaber","email":"","orcid":"","institution":"Queen Mary University of London","correspondingAuthor":false,"prefix":"","firstName":"Mona","middleName":"","lastName":"Jaber","suffix":""}],"badges":[],"createdAt":"2026-01-19 12:40:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8639560/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8639560/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101751583,"identity":"73e0af22-f9cc-4cb9-b74e-2a458c9e96c9","added_by":"auto","created_at":"2026-02-03 10:21:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":580319,"visible":true,"origin":"","legend":"","description":"","filename":"TemplateforsubmissionstoScientificReports11.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8639560/v1_covered_33758766-eef6-4a00-b5ce-28f02535bfe0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Low-complexity pedestrian intent prediction using contextual stacked ensemble learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8639560/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8639560/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Walking, as a form of active and sustainable mobility, plays a critical role in future smart transportation systems. Accurate prediction of pedestrian crossing intentions is essential for preventing collisions, particularly with the increasing deployment of autonomous vehicles.Existing approaches to near-miss prevention typically rely on computationally intensive computer vision and deep learning techniques. In contrast, this work proposes CSE, a lightweight contextual stacked ensemble-learning framework to efficiently predict pedestrian crossing intent. Pedestrians are first detected and their visual representation is compressed through skeletonization, and complementary pose, trajectory, and contextual cues are fused using a stacked ensemble model.Experimental results on multiple datasets demonstrate that the proposed approach achieves performance comparable to state-of-the-art pedestrian intent prediction methods while reducing computational complexity by at least $25$ times. This reduction translates directly into a $25\\times$ decrease in inference time, enabling deployment on resource-constrained edge devices without compromising accuracy and while avoiding the latency associated with cloud-based processing.","manuscriptTitle":"Low-complexity pedestrian intent prediction using contextual stacked ensemble learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-30 04:22:38","doi":"10.21203/rs.3.rs-8639560/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-13T17:04:07+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"299497668285074461074645355602197658968","date":"2026-03-01T10:44:04+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-26T15:50:50+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-26T10:15:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-25T01:19:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"2413433793317647717312571416899933393","date":"2026-02-23T02:27:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"127632826672776918773426824259408969298","date":"2026-01-31T14:17:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"90270314764534927391350958580009192870","date":"2026-01-30T09:20:40+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-30T07:06:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"79844548458894484721875676642980827897","date":"2026-01-30T06:41:18+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-28T02:38:31+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-27T05:06:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-22T05:11:05+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-22T05:10:31+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-01-19T12:31:58+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5e3984f9-8399-4270-9b06-ffc42c2736bf","owner":[],"postedDate":"January 30th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":61909211,"name":"Physical sciences/Engineering"},{"id":61909212,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-06T09:08:44+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-30 04:22:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8639560","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8639560","identity":"rs-8639560","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}