Intelligent Vehicle Object Detection Based on Improved YOLOv7 Algorithm

Intelligent Vehicle Object Detection Based on Improved YOLOv7 Algorithm | 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 Intelligent Vehicle Object Detection Based on Improved YOLOv7 Algorithm Aijuan Li, Chunpeng Gong, Dongjin Guo, Guangkai Du, Weikai He, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4538660/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 Intelligent driving of automobiles is based on environment awareness, and the technology that makes environment perception possible is target detection. Road traffic scenarios are complicated and variable, which can lead to issues including misdetection and omission of small objects and obscured areas. Furthermore, because to their limited processing capacity, intelligent cars must not only have a high detection accuracy and speed but also a low-complexity model in order to lessen their reliance on high-performance computing platforms. When compared to other lightweight models, the lightweight version of the YOLOv7 algorithm offers a lot of opportunity for improvement in terms of processing and parameter count. Thus, based on the enhanced YOLOv7 algorithm, this research suggests an intelligent vehicle target recognition technique. The YOLOv7-tiny network structure serves as the foundation for the addition of a small target detection layer, the introduction of a context aggregation module to enhance the feature extraction process and the model's capacity to detect small targets in complex scenarios, the reconfiguration of the SPPCSPC module to speed up detection, and the proposal of the P-ELEN module, which reduces the model's number of parameters and computation load, to lessen redundant computation and memory access. Nine sets of comparison tests, eight sets of ablation experiments, and detection effects are used to validate the enhanced YOLOv7 algorithm's detection performance. The experimental findings demonstrate that the enhanced YOLOv7 algorithm increases detection accuracy while simultaneously decreasing model complexity. Physical sciences/Engineering Physical sciences/Mathematics and computing Physical sciences/Physics YOLOv7 intelligent vehicle target detection Full Text Additional Declarations No competing interests reported. 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-4538660","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":318246112,"identity":"b85d5dd0-8b48-41c7-a868-1a1933cc0baf","order_by":0,"name":"Aijuan Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIie3RsQqCQBjA8U8ObBFdT4R6hYsgCKJn8RCaIoRAgoaEwNXV3kIImi8cXMTWG+sNCl+gO8n1dAy6//Qh34/zOACd7gezEQDDYnAACGk/sR5idsSNBWGDSDeIdQLDyAg92SJZbWf3It+9Exjb3DeaUPljJmFuEuzmfB2SWwIzl/vIy9R3kQTRK7eIJDTnvoksJRm9BDnSS1q15DiAWPKUguawaYlPBpCQ4bqkmbxLVePpuXqePBVxnPLS4OhA07S4kn20nNhlcGtURIbw90Tx+nI04h4gVl5f+uhd1el0ur/sA1W3Sy+FR1YRAAAAAElFTkSuQmCC","orcid":"","institution":"Shandong Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Aijuan","middleName":"","lastName":"Li","suffix":""},{"id":318246116,"identity":"62e1691b-caed-4b2f-b283-669d29a863a8","order_by":1,"name":"Chunpeng Gong","email":"","orcid":"","institution":"Shandong Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Chunpeng","middleName":"","lastName":"Gong","suffix":""},{"id":318246119,"identity":"e4774bf0-dd46-452b-a498-ff99c160b414","order_by":2,"name":"Dongjin Guo","email":"","orcid":"","institution":"Shandong Huali electromechanical Co., LTD","correspondingAuthor":false,"prefix":"","firstName":"Dongjin","middleName":"","lastName":"Guo","suffix":""},{"id":318246121,"identity":"e4fe41c6-acfe-45d3-8dd5-47f026f2c32c","order_by":3,"name":"Guangkai Du","email":"","orcid":"","institution":"Shandong Huali electromechanical Co., LTD","correspondingAuthor":false,"prefix":"","firstName":"Guangkai","middleName":"","lastName":"Du","suffix":""},{"id":318246122,"identity":"daa62abc-3f39-404d-b7b5-4d1f508b9048","order_by":4,"name":"Weikai He","email":"","orcid":"","institution":"Shandong Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Weikai","middleName":"","lastName":"He","suffix":""},{"id":318246123,"identity":"841a36f3-0038-4feb-a702-6763b637a9b3","order_by":5,"name":"Vladimir Zyrianov","email":"","orcid":"","institution":"Rostov-on-don City","correspondingAuthor":false,"prefix":"","firstName":"Vladimir","middleName":"","lastName":"Zyrianov","suffix":""}],"badges":[],"createdAt":"2024-06-06 08:48:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4538660/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4538660/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":62277177,"identity":"82c0db09-0839-4ca8-b1e4-2cd4c9473c3b","added_by":"auto","created_at":"2024-08-12 11:37:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1700834,"visible":true,"origin":"","legend":"","description":"","filename":"IntelligentVehicleObjectDetectionsubmit1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4538660/v1_covered_dbc559db-2ff0-4cda-bb9c-42f22992a75f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Intelligent Vehicle Object Detection Based on Improved YOLOv7 Algorithm","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"YOLOv7, intelligent vehicle, target detection","lastPublishedDoi":"10.21203/rs.3.rs-4538660/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4538660/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Intelligent driving of automobiles is based on environment awareness, and the technology that makes environment perception possible is target detection. Road traffic scenarios are complicated and variable, which can lead to issues including misdetection and omission of small objects and obscured areas. Furthermore, because to their limited processing capacity, intelligent cars must not only have a high detection accuracy and speed but also a low-complexity model in order to lessen their reliance on high-performance computing platforms. When compared to other lightweight models, the lightweight version of the YOLOv7 algorithm offers a lot of opportunity for improvement in terms of processing and parameter count. Thus, based on the enhanced YOLOv7 algorithm, this research suggests an intelligent vehicle target recognition technique. The YOLOv7-tiny network structure serves as the foundation for the addition of a small target detection layer, the introduction of a context aggregation module to enhance the feature extraction process and the model's capacity to detect small targets in complex scenarios, the reconfiguration of the SPPCSPC module to speed up detection, and the proposal of the P-ELEN module, which reduces the model's number of parameters and computation load, to lessen redundant computation and memory access. Nine sets of comparison tests, eight sets of ablation experiments, and detection effects are used to validate the enhanced YOLOv7 algorithm's detection performance. The experimental findings demonstrate that the enhanced YOLOv7 algorithm increases detection accuracy while simultaneously decreasing model complexity.","manuscriptTitle":"Intelligent Vehicle Object Detection Based on Improved YOLOv7 Algorithm","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-27 03:15:50","doi":"10.21203/rs.3.rs-4538660/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":"51c8c64e-44ee-4c61-a7a6-dbe26c489c4b","owner":[],"postedDate":"June 27th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":33647254,"name":"Physical sciences/Engineering"},{"id":33647255,"name":"Physical sciences/Mathematics and computing"},{"id":33647256,"name":"Physical sciences/Physics"}],"tags":[],"updatedAt":"2024-08-12T11:29:21+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-27 03:15:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4538660","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4538660","identity":"rs-4538660","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}