YOLOv8-MCDE: A Lightweight Model for Detecting Small Instruments in Complex Environments from Inspection Robots’ Perspective

YOLOv8-MCDE: A Lightweight Model for Detecting Small Instruments in Complex Environments from Inspection Robots’ Perspective | 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 YOLOv8-MCDE: A Lightweight Model for Detecting Small Instruments in Complex Environments from Inspection Robots’ Perspective Tongxin Yang, Ding Ling, Qingwu Shi, Tianyue Jiang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6644483/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 Sep, 2025 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract This paper addresses the challenges of equipment inspection in complex substation environments by proposing a lightweight small object detection algorithm, YOLOv8-MCDE, specifically designed for instrument recognition and suitable for deployment on inspection robots. Through model structure optimization, the proposed method significantly enhances both the small object detection performance and real-time efficiency of instrument detection on edge computing devices. YOLOv8-MCDE adopts the lightweight MobileNetV3 architecture as its backbone, effectively reducing model complexity and improving operational efficiency. The neck integrates a CNN-based Cross-scale Feature Fusion (CCFF) algorithm, which further lowers computational overhead while enhancing detection capability for small objects. In addition, a Deformable Large Kernel Attention (D-LKA) mechanism is integrated to increase the model’s sensitivity to small objects within complex backgrounds. The conventional CIOU loss function is also replaced with the more efficient EIOU loss function, significantly improving bounding box localization accuracy and accelerating model convergence. Experimental results demonstrate that YOLOv8-MCDE achieves a Precision of 92.80% and an mAP50 of 91.36%, representing improvements of 2.38% and 1.27%, respectively, compared to the original YOLOv8. Furthermore, the proposed algorithm reduces FLOPs by 37.68% and model size by 36%. These enhancements substantially reduce computational resource demands while significantly improving the real-time detection capabilities and small object recognition performance of inspection robots operating in complex environments. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Engineering/Mechanical engineering Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 01 Sep, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 30 Jun, 2025 Reviews received at journal 26 Jun, 2025 Reviewers agreed at journal 25 Jun, 2025 Reviews received at journal 24 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers invited by journal 30 May, 2025 Editor assigned by journal 30 May, 2025 Editor invited by journal 26 May, 2025 Submission checks completed at journal 24 May, 2025 First submitted to journal 12 May, 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-6644483","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":464447016,"identity":"a372a4fc-6add-49ee-9f29-e174bbda5b7d","order_by":0,"name":"Tongxin Yang","email":"","orcid":"","institution":"Jiamusi University","correspondingAuthor":false,"prefix":"","firstName":"Tongxin","middleName":"","lastName":"Yang","suffix":""},{"id":464447018,"identity":"cc695a2d-8efa-43a3-98e9-3cd0d76ed1cf","order_by":1,"name":"Ding Ling","email":"","orcid":"","institution":"Jiamusi University","correspondingAuthor":false,"prefix":"","firstName":"Ding","middleName":"","lastName":"Ling","suffix":""},{"id":464447019,"identity":"c53fed4b-c727-4558-979a-e73b33b2d247","order_by":2,"name":"Qingwu Shi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYDACCcYGhgQQg70hASJygGgtPAeI1gJnQHUQ1CI/u7nxxsMdtYkbbj54uvFnG4Mc340Exs8FeLQY3DnYbJF45njihtsJabd52xiMJW8kMEvPwKdFIrENiI7lgrUwtjEkbriRwMbMg89hM2Babh5Iuwl0WD1BLQw3wFpqcjfcYEi7AXRYggEhLQY3EoF+aTtQP/MM0GE85yQMZ5552CyN32HpD4HuqTPmO34m7eaPMht5vuPJBz/jdRgDOGoOAymeBAibARi5hABQWR2QYj9AUOUoGAWjYBSMTAAALtRX6gGOY6YAAAAASUVORK5CYII=","orcid":"","institution":"Jiamusi University","correspondingAuthor":true,"prefix":"","firstName":"Qingwu","middleName":"","lastName":"Shi","suffix":""},{"id":464447021,"identity":"e9cf6648-816f-4533-8535-ee14ef67a370","order_by":3,"name":"Tianyue Jiang","email":"","orcid":"","institution":"Jiamusi University","correspondingAuthor":false,"prefix":"","firstName":"Tianyue","middleName":"","lastName":"Jiang","suffix":""}],"badges":[],"createdAt":"2025-05-12 08:23:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6644483/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6644483/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-17186-9","type":"published","date":"2025-09-01T15:57:47+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":90827983,"identity":"a6d54104-a83e-4642-9dca-e59dbad9510a","added_by":"auto","created_at":"2025-09-08 16:04:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6661365,"visible":true,"origin":"","legend":"","description":"","filename":"YOLOv8MCDEALightweightModelforDetectingSmallInstrumentsinComplexEnvironmentsfromInspectionRobotsPerspective.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6644483/v1_covered_e2f8911d-2417-4ecd-badf-430075abed98.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eYOLOv8-MCDE: A Lightweight Model for Detecting Small Instruments in Complex Environments from Inspection Robots’ Perspective\u003c/p\u003e","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-6644483/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6644483/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This paper addresses the challenges of equipment inspection in complex substation environments by proposing a lightweight small object detection algorithm, YOLOv8-MCDE, specifically designed for instrument recognition and suitable for deployment on inspection robots. Through model structure optimization, the proposed method significantly enhances both the small object detection performance and real-time efficiency of instrument detection on edge computing devices. YOLOv8-MCDE adopts the lightweight MobileNetV3 architecture as its backbone, effectively reducing model complexity and improving operational efficiency. The neck integrates a CNN-based Cross-scale Feature Fusion (CCFF) algorithm, which further lowers computational overhead while enhancing detection capability for small objects. In addition, a Deformable Large Kernel Attention (D-LKA) mechanism is integrated to increase the model’s sensitivity to small objects within complex backgrounds. The conventional CIOU loss function is also replaced with the more efficient EIOU loss function, significantly improving bounding box localization accuracy and accelerating model convergence. Experimental results demonstrate that YOLOv8-MCDE achieves a Precision of 92.80% and an mAP50 of 91.36%, representing improvements of 2.38% and 1.27%, respectively, compared to the original YOLOv8. Furthermore, the proposed algorithm reduces FLOPs by 37.68% and model size by 36%. These enhancements substantially reduce computational resource demands while significantly improving the real-time detection capabilities and small object recognition performance of inspection robots operating in complex environments.","manuscriptTitle":"YOLOv8-MCDE: A Lightweight Model for Detecting Small Instruments in Complex Environments from Inspection Robots’ Perspective","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-02 18:24:53","doi":"10.21203/rs.3.rs-6644483/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-30T06:50:50+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-26T10:46:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"269336253477916403817894815182197945777","date":"2025-06-26T01:25:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-24T08:14:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"77589880934612590070573937715660419395","date":"2025-06-04T09:21:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"82623801921691575817996944267225741242","date":"2025-06-04T05:26:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-30T11:46:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-30T11:23:44+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-26T14:19:42+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-24T09:19:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-12T08:19:22+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":"5551862d-1f47-491b-9168-16368b9c46a5","owner":[],"postedDate":"June 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":49410490,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":49410491,"name":"Physical sciences/Engineering/Mechanical engineering"}],"tags":[],"updatedAt":"2025-09-08T16:00:53+00:00","versionOfRecord":{"articleIdentity":"rs-6644483","link":"https://doi.org/10.1038/s41598-025-17186-9","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-09-01 15:57:47","publishedOnDateReadable":"September 1st, 2025"},"versionCreatedAt":"2025-06-02 18:24:53","video":"","vorDoi":"10.1038/s41598-025-17186-9","vorDoiUrl":"https://doi.org/10.1038/s41598-025-17186-9","workflowStages":[]},"version":"v1","identity":"rs-6644483","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6644483","identity":"rs-6644483","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}