A Semi-Supervised Domain Adaptive Learning Approach to Unstructured Road Region Semantic Segmentation for Greenhouse Robots

A Semi-Supervised Domain Adaptive Learning Approach to Unstructured Road Region Semantic Segmentation for Greenhouse Robots | 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 A Semi-Supervised Domain Adaptive Learning Approach to Unstructured Road Region Semantic Segmentation for Greenhouse Robots Bishu GAO, liang Gong, Wei ZHANG, Yingxin WU, Gengjie LIN, Zekai Zhang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1981444/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 May, 2026 Read the published version in Soft Computing → Version 1 posted 6 You are reading this latest preprint version Abstract Efficient drivable region segmentation is a critical for greenhouse robot navigation. State-of-the-art deep learning based road segmentation methods rely largely on labeled datasets to deal with the complexity of unstructured facility agriculture environment. However, the scarcity of annotated datasets limits the model performance. To break the bottleneck, this paper proposes a semi-supervised domain adaptive learning method for unstructured road semantic segmentation. Firstly, we establish a training framework for segmentation models through the transfer learning approach from a synthetic road dataset to an unstructured road dataset. Secondly, we determine the optimal pre-training strategy for solving the greenhouse road segmentation problem. Finally, for the long-tailed distribution of image data in the process of drivable area segmentation, we optimize the loss function to obtain an effective segmentation model for greenhouse robot navigation. For unstructured facility farming scenarios, we created an unstructured road dataset with annotation. Experiments show that, with a small number of labeled data, the road mIoU reaches 98.6%, which is about 10% greater than the existing unstructured road segmentation models to deal with ambiguous boundaries, complex obstacles, and shadow interference. It shows that the proposed method is feasible to leverage the successful existing city self-driving models and datasets to enrich and improve the road segmentation under agricultural scenarios. Greenhouse robot Semi-supervised Domain adaptive Unstructured road Semantic segmentation Full Text Cite Share Download PDF Status: Published Journal Publication published 21 May, 2026 Read the published version in Soft Computing → Version 1 posted Editorial decision: Major Revision 27 Sep, 2023 Reviewers agreed at journal 02 Jul, 2023 Reviewers invited by journal 16 Jun, 2023 Editor invited by journal 21 Feb, 2023 Editor assigned by journal 22 Aug, 2022 First submitted to journal 20 Aug, 2022 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-1981444","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":210480441,"identity":"cdb844bf-9ee9-4933-ad06-927a88c50608","order_by":0,"name":"Bishu GAO","email":"","orcid":"","institution":"Shanghai Jiao Tong University School of Mechanical Engineering","correspondingAuthor":false,"prefix":"","firstName":"Bishu","middleName":"","lastName":"GAO","suffix":""},{"id":210480442,"identity":"6dd79f32-3736-45e7-b44d-15dd9b61fe72","order_by":1,"name":"liang Gong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABA0lEQVRIiWNgGAWjYLCCBwYQ+sAHBjYwQ4KglgSoloMzGNgkiNQCpZl5oKrxapF37z38IqHALk/egTvxsM0fvjqDA8wHb/Mw2OXh0mJ45lyaRYJBcrHhAd4Nh3Pb2CQMDrAlW/MwJBfj1DIjx8wgwYA5cWMDSEsDSAuPmTQPw4HEBvxa6iFaLP6AtPB/w6tFXiLH+EGCweHE+QxALQxsYFvY8Gox4DljBgzk44kbgFoO9raxSc48zGZsOccgGbct7T3GHz78qU6c38C7+cOPP8f4+Y43P7zxpsIOty0HoLFncP8BiDoGjB0wF4d6kC0NDMwfoAwQqMGtdBSMglEwCkYsAADhZ1e+mIkzcAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-0265-1192","institution":"Shanghai Jiao Tong University School of Mechanical Engineering","correspondingAuthor":true,"prefix":"","firstName":"liang","middleName":"","lastName":"Gong","suffix":""},{"id":210480443,"identity":"aa338c52-f2d6-47e3-b64a-be50636d2c85","order_by":2,"name":"Wei ZHANG","email":"","orcid":"","institution":"Shanghai Jiao Tong University School of Mechanical Engineering","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"ZHANG","suffix":""},{"id":210480444,"identity":"980e304a-7584-44e6-a9c6-71bd9e10c95c","order_by":3,"name":"Yingxin WU","email":"","orcid":"","institution":"Shanghai Jiao Tong University School of Mechanical Engineering","correspondingAuthor":false,"prefix":"","firstName":"Yingxin","middleName":"","lastName":"WU","suffix":""},{"id":210480445,"identity":"0bfc08c4-ec39-4e46-814d-582fb58f59be","order_by":4,"name":"Gengjie LIN","email":"","orcid":"","institution":"Shanghai Jiao Tong University School of Mechanical Engineering","correspondingAuthor":false,"prefix":"","firstName":"Gengjie","middleName":"","lastName":"LIN","suffix":""},{"id":210480446,"identity":"a0f900d4-b37b-4717-8f04-a4c2298396a7","order_by":5,"name":"Zekai Zhang","email":"","orcid":"","institution":"Shanghai Jiao Tong University School of Mechanical Engineering","correspondingAuthor":false,"prefix":"","firstName":"Zekai","middleName":"","lastName":"Zhang","suffix":""},{"id":210480447,"identity":"f3838715-1cde-4c65-b50a-0ce1aeeb38dd","order_by":6,"name":"Yanming LI","email":"","orcid":"","institution":"Shanghai Jiao Tong University School of Mechanical Engineering","correspondingAuthor":false,"prefix":"","firstName":"Yanming","middleName":"","lastName":"LI","suffix":""},{"id":210480448,"identity":"49fe44f2-17ac-4086-a85a-acf4da8771a2","order_by":7,"name":"Chengliang LIU","email":"","orcid":"","institution":"Shanghai Jiao Tong University School of Mechanical Engineering","correspondingAuthor":false,"prefix":"","firstName":"Chengliang","middleName":"","lastName":"LIU","suffix":""}],"badges":[],"createdAt":"2022-08-20 15:21:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-1981444/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-1981444/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00500-026-11381-0","type":"published","date":"2026-05-21T17:09:05+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":110508330,"identity":"63bb350a-b445-4a3c-85a4-ddbb392f5651","added_by":"auto","created_at":"2026-06-01 17:48:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":398341,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1981444/v1_covered_6122aa18-d58a-4399-9f93-e6487d7ab8a8.pdf"}],"financialInterests":"","formattedTitle":"A Semi-Supervised Domain Adaptive Learning Approach to Unstructured Road Region Semantic Segmentation for Greenhouse Robots","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":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Greenhouse robot, Semi-supervised, Domain adaptive, Unstructured road, Semantic segmentation","lastPublishedDoi":"10.21203/rs.3.rs-1981444/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1981444/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEfficient drivable region segmentation is a critical for greenhouse robot navigation. State-of-the-art deep learning based road segmentation methods rely largely on labeled datasets to deal with the complexity of unstructured facility agriculture environment. However, the scarcity of annotated datasets limits the model performance. To break the bottleneck, this paper proposes a semi-supervised domain adaptive learning method for unstructured road semantic segmentation. Firstly, we establish a training framework for segmentation models through the transfer learning approach from a synthetic road dataset to an unstructured road dataset. Secondly, we determine the optimal pre-training strategy for solving the greenhouse road segmentation problem. Finally, for the long-tailed distribution of image data in the process of drivable area segmentation, we optimize the loss function to obtain an effective segmentation model for greenhouse robot navigation. For unstructured facility farming scenarios, we created an unstructured road dataset with annotation. Experiments show that, with a small number of labeled data, the road mIoU reaches 98.6%, which is about 10% greater than the existing unstructured road segmentation models to deal with ambiguous boundaries, complex obstacles, and shadow interference. It shows that the proposed method is feasible to leverage the successful existing city self-driving models and datasets to enrich and improve the road segmentation under agricultural scenarios.\u003c/p\u003e","manuscriptTitle":"A Semi-Supervised Domain Adaptive Learning Approach to Unstructured Road Region Semantic Segmentation for Greenhouse Robots","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-06-20 06:39:53","doi":"10.21203/rs.3.rs-1981444/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major Revision","date":"2023-09-28T03:33:52+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2023-07-02T05:16:23+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-06-16T09:58:17+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"Soft Computing","date":"2023-02-21T17:16:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2022-08-22T15:02:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"Soft Computing","date":"2022-08-20T11:20:17+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"97a5cbf4-aa22-4be6-8b12-4b49f40e3a1b","owner":[],"postedDate":"June 20th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-06-01T17:41:56+00:00","versionOfRecord":{"articleIdentity":"rs-1981444","link":"https://doi.org/10.1007/s00500-026-11381-0","journal":{"identity":"soft-computing","isVorOnly":false,"title":"Soft Computing"},"publishedOn":"2026-05-21 17:09:05","publishedOnDateReadable":"May 21st, 2026"},"versionCreatedAt":"2023-06-20 06:39:53","video":"","vorDoi":"10.1007/s00500-026-11381-0","vorDoiUrl":"https://doi.org/10.1007/s00500-026-11381-0","workflowStages":[]},"version":"v1","identity":"rs-1981444","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1981444","identity":"rs-1981444","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}