Pedestrian Detection in Aerial Image Based on Convolutional Neural Network with Attention Mechanism and Multi-scale Prediction

Pedestrian Detection in Aerial Image Based on Convolutional Neural Network with Attention Mechanism and Multi-scale Prediction | 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 Pedestrian Detection in Aerial Image Based on Convolutional Neural Network with Attention Mechanism and Multi-scale Prediction Jiaxi Yang, Jiaquan Shen, Shitong Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7333218/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 12 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Pedestrian object detection is crucial in intelligent systems such as traffic management and surveillance. Traditional machine learning methods have shown drawbacks, including low accuracy and slow processing. Convolutional Neural Network (CNN)-based algorithms have achieved notable progress, but mainstream CNNs still struggle with slow speed and low accuracy, particularly for small and occluded targets from aerial perspectives. In this paper, we propose a Multi-Scale Attention YOLO (MSA-YOLO) algorithm to address these issues. MSA-YOLO incorporates a Squeeze, Excitation, and Cross Stage Partial (SECSP) channel attention module to extract richer pedestrian features with minimal additional parameters. A multi-scale prediction module is also introduced to capture information across different scales, improving small object detection and reducing missed detections. To evaluate our approach, we manually collect and annotate the Aerial Pedestrian Dataset (AP Dataset), which, to our knowledge, provides more annotations, varied scenes, and diverse view angles than comparable existing datasets. The high-resolution images in the AP Dataset allow for capturing more detailed pedestrian features, which can enhance model performance. Experimental results show that, on the AP dataset, MSA-YOLO demonstrates clear advantages over several widely used object detection and pedestrian detection models developed in recent years, indicating its potential dual benefits in terms of accuracy and efficiency. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 12 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 01 Sep, 2025 Reviews received at journal 29 Aug, 2025 Reviews received at journal 21 Aug, 2025 Reviewers agreed at journal 19 Aug, 2025 Reviewers agreed at journal 19 Aug, 2025 Reviewers invited by journal 19 Aug, 2025 Editor assigned by journal 19 Aug, 2025 Editor invited by journal 14 Aug, 2025 Submission checks completed at journal 13 Aug, 2025 First submitted to journal 13 Aug, 2025 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-7333218","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":503668598,"identity":"67247ffe-4964-4582-aa66-0d0772c566f7","order_by":0,"name":"Jiaxi Yang","email":"","orcid":"","institution":"Concordia University","correspondingAuthor":false,"prefix":"","firstName":"Jiaxi","middleName":"","lastName":"Yang","suffix":""},{"id":503668599,"identity":"be46f732-76da-4ada-ac3d-df9f05e6d5ff","order_by":1,"name":"Jiaquan Shen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9klEQVRIiWNgGAWjYDACCRA2gHNtePj5G0jTkiYjOeMAEVqQwGEbg4YE/DrkZzcfe2BRYCe74fjZAww/287zGDAcYPzwMQe3FoM7x9INJAySjTecyUtg7G27zWPO3MAsOXMbHi0SOWYSEgbMiRsO5BgwM5y5zWPZcICNmRePFvkZ+d+AWuoTN5x/A9JyjsfgQAJ+LQw3ctiAWg4nbrgBsqXiAGEtBjfSQA47bjzzxhsDxp6KZB7JGQeb8fpFfkbyM2mJP9WyfedzDBh+GNjZ8/M3H/zwEZ/DgIAZGDeMDQwM7D8gfBCbAGD8QJSyUTAKRsEoGLEAAFbCTwI/nmc3AAAAAElFTkSuQmCC","orcid":"","institution":"Luoyang Normal University","correspondingAuthor":true,"prefix":"","firstName":"Jiaquan","middleName":"","lastName":"Shen","suffix":""},{"id":503668600,"identity":"65cea474-125e-4f7e-9934-76757a1e5cf1","order_by":2,"name":"Shitong Wang","email":"","orcid":"","institution":"Universiti Sains Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Shitong","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-08-09 10:23:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7333218/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7333218/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-27441-8","type":"published","date":"2025-12-12T15:57:10+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":98243495,"identity":"82ccaf5c-ac3f-4e31-bada-3105df4386e5","added_by":"auto","created_at":"2025-12-15 16:06:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":13953986,"visible":true,"origin":"","legend":"","description":"","filename":"PedestrianDetectioninAerialImageBasedonConvolutionalNeuralNetworkwithAttentionMechanismandMultiscalePrediction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7333218/v1_covered_a254b0ee-a032-4bac-af11-312129d346b2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Pedestrian Detection in Aerial Image Based on Convolutional Neural Network with Attention Mechanism and Multi-scale Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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-7333218/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7333218/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Pedestrian object detection is crucial in intelligent systems such as traffic management and surveillance. Traditional machine learning methods have shown drawbacks, including low accuracy and slow processing. Convolutional Neural Network (CNN)-based algorithms have achieved notable progress, but mainstream CNNs still struggle with slow speed and low accuracy, particularly for small and occluded targets from aerial perspectives. In this paper, we propose a Multi-Scale Attention YOLO (MSA-YOLO) algorithm to address these issues. MSA-YOLO incorporates a Squeeze, Excitation, and Cross Stage Partial (SECSP) channel attention module to extract richer pedestrian features with minimal additional parameters. A multi-scale prediction module is also introduced to capture information across different scales, improving small object detection and reducing missed detections. To evaluate our approach, we manually collect and annotate the Aerial Pedestrian Dataset (AP Dataset), which, to our knowledge, provides more annotations, varied scenes, and diverse view angles than comparable existing datasets. The high-resolution images in the AP Dataset allow for capturing more detailed pedestrian features, which can enhance model performance. Experimental results show that, on the AP dataset, MSA-YOLO demonstrates clear advantages over several widely used object detection and pedestrian detection models developed in recent years, indicating its potential dual benefits in terms of accuracy and efficiency.","manuscriptTitle":"Pedestrian Detection in Aerial Image Based on Convolutional Neural Network with Attention Mechanism and Multi-scale Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-27 06:24:51","doi":"10.21203/rs.3.rs-7333218/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-01T07:31:04+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-29T06:27:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-21T12:23:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"222871926034683522570054774962653272037","date":"2025-08-19T08:21:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"43897221474135595154666355035820843816","date":"2025-08-19T08:03:38+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-19T07:49:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-19T07:47:54+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-08-14T11:49:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-13T14:36:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-08-13T14:34:41+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":"78a25171-3c28-4f02-8d89-e38a35d89cb2","owner":[],"postedDate":"August 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":53510679,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":53510680,"name":"Physical sciences/Engineering"},{"id":53510681,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-12-15T16:00:31+00:00","versionOfRecord":{"articleIdentity":"rs-7333218","link":"https://doi.org/10.1038/s41598-025-27441-8","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-12 15:57:10","publishedOnDateReadable":"December 12th, 2025"},"versionCreatedAt":"2025-08-27 06:24:51","video":"","vorDoi":"10.1038/s41598-025-27441-8","vorDoiUrl":"https://doi.org/10.1038/s41598-025-27441-8","workflowStages":[]},"version":"v1","identity":"rs-7333218","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7333218","identity":"rs-7333218","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}