[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84218-en":3,"doc-seo-84218-105":28,"detail-sidebar-cat-0-en-105":89},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":13,"seo_description":14,"update_tm":26,"read_time":27},84218,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","PLED-VINS: A Point-Line Event-Based Visual Inertial SLAM for Dynamic Environments","Dynamic environments pose a core challenge for visual SLAM because moving objects and rapid motion introduce unreliable observations that degrade state estimation. PLED-VINS presents a monocular event-camera-based visual-inertial SLAM framework designed for dynamic scenes. The method builds an entropy–recency score map to quantify temporal reliability for point and line features using event temporal statistics, estimates geometric reliability through unified point–line robust bundle adjustment, and fuses both via adaptive weighting to suppress unreliable observations. Experiments validate improved pose accuracy on dynamic sequences.","PLED-VINS: A Point-Line Event-Based Visual Inertial SLAM for  \nDynamic Environments  \nSeunghun Lee 1†, Jihun Nam2†, Dong-Uk Seo2 , and Hyun Myung2∗ , Senior Member, IEEE  \narXiv :2607 .07374v 1 [ cs .RO] 8 Jul 2026  \nAbstract—Dynamic environments remain a fundamental challenge for visual SLAM, where unreliable observations from moving objects and rapid motion degrade state estimation accuracy. Although event cameras preserve fine-grained spatiotemporal information, most existing event-based SLAM frameworks still assume static scenes and lack approaches to estimate the reliability of features. To this end, we propose PLEDVINS, a monocular event camera-based visual-inertial SLAM framework that enables robust state estimation in dynamic environments. We propose an entropy-recency score map to characterize the temporal reliability of both point and line features based on event temporal statistics. Concurrently, geometric reliability is estimated via a unified point–line robust bundle adjustment. Building upon these, we design an adaptive weighting strategy that fuses temporal and geometric reliability, including motion-conditioned reliability modeling for line features, to suppress unreliable observations. Experimental results demonstrate that PLED-VINS improves state estimation on the evaluated dynamic sequences with moving objects.  \nI. INTRODUCTION  \nMost visual simultaneous localization and mapping (SLAM) systems have been developed under the assumption of a static environment. This assumption, however, is frequently violated in dynamic scenes, where moving objects introduce erroneous geometric constraints during optimization, degrading pose estimation accuracy. Although several frame-based dynamic SLAM methods have attempted to identify dynamic objects or adjust feature weights [1]–[7], these methods remain fragile in highly aggressive scenarios, due to motion-blurred frame observations.  \nEvent cameras [10] help address the limitations of framebased cameras in low-light and high-speed motion scenes. By asynchronously recording per-pixel brightness changes, event cameras achieve high temporal resolution, enabling precise analysis of instantaneous motion. Despite the advantages, the majority of event-based SLAM frameworks [11]–[15] assume static environments. One promising direction is to integrate event-based motion segmentation into SLAM for dynamic scenes. Existing methods based on contrast maximization and clustering [16]–[18], however, are computationally expensive and introduce substantial integration overhead, limiting their real-time applicability for state estimation. Thus, a unified event-based SLAM framework that efficiently incorporates dynamic information remains underexplored.  \n∗ Corresponding author: Hyun Myung.  \n†Both authors have equally contributed.  \n1Robotics Program, KAIST (Korea Advanced Institute of Science and Technology), Daejeon, 34141, [South Korea.](South Korea. shleee@kaist.ac.kr)[ shleee@kaist.ac.kr](South Korea. shleee@kaist.ac.kr)  \n2 School of Electrical Engineering, KAIST (Korea Advanced Institute of Science and Technology), Daejeon, 34141, South Korea. {namjh1228, dongukseo, [hmyung](hmyung}@kaist.ac.kr)[}](hmyung}@kaist.ac.kr)[@kaist.ac.kr](hmyung}@kaist.ac.kr)  \n\n| \u003Cbr>Static |\n| --- |\n| \u003Cbr>Dynamic |\n\n(b)  \nFig. 1. Our algorithm, PLED-VINS, in dynamic environments. (a) Weighted line features and estimated trajectory on parking   lot high sequence of VIODE dataset [8] . (b) Weighted point features and event streams on zurich   city   01 e sequence of DSEC dataset [9] . Green and red indicate high and low feature weights, respectively.  \nIn this context, we propose PLED-VINS, a robust monocular event camera-based visual-inertial SLAM framework for dynamic environments. As illustrated in Fig. 1, PLED-VINS incorporates feature-level temporal and bundle adjustment (BA)-based geometric reliability cues for real-time performance instead of explicit object-level segmentation. Event cameras offer","cbCaitELJ6CBWBFE","https://ap.wps.com/l/cbCaitELJ6CBWBFE","pdf",3090676,1,"English","en",105,"# Introduction\n# Related Works\n## Feature-based Event SLAM\n## Event Motion Segmentation for Dynamic Scenes","[{\"question\":\"What problem does PLED-VINS address in visual SLAM?\",\"answer\":\"PLED-VINS targets degraded state estimation in dynamic environments, where moving objects produce unreliable geometric constraints during optimization.\"},{\"question\":\"How does PLED-VINS estimate temporal reliability for features?\",\"answer\":\"It constructs an entropy–recency score map from event temporal statistics, evaluating recency and distribution of events to assign reliability weights to point and line features.\"},{\"question\":\"How are temporal and geometric reliabilities combined?\",\"answer\":\"PLED-VINS estimates geometric reliability using unified point–line robust bundle adjustment, then uses an adaptive weighting strategy to fuse temporal and geometric cues to suppress unreliable observations.\"}]",1784194096,20,{"code":4,"msg":29,"data":30},"ok",{"site_id":23,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":26},"pled-vins-a-point-line-event-based-visual-inertial-slam-for-dynamic-environments","",{"@graph":34,"@context":83},[35,52,66],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/pled-vins-a-point-line-event-based-visual-inertial-slam-for-dynamic-environments/84218/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does PLED-VINS address in visual SLAM?","Question",{"text":73,"@type":74},"PLED-VINS targets degraded state estimation in dynamic environments, where moving objects produce unreliable geometric constraints during optimization.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How does PLED-VINS estimate temporal reliability for features?",{"text":78,"@type":74},"It constructs an entropy–recency score map from event temporal statistics, evaluating recency and distribution of events to assign reliability weights to point and line features.",{"name":80,"@type":71,"acceptedAnswer":81},"How are temporal and geometric reliabilities combined?",{"text":82,"@type":74},"PLED-VINS estimates geometric reliability using unified point–line robust bundle adjustment, then uses an adaptive weighting strategy to fuse temporal and geometric cues to suppress unreliable observations.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,125,128,132],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":44,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":44,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":44,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":44,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":44,"category_name":123,"show_sort_weight":27,"slug":124},9,"Religion & Spirituality","religion-spirituality",{"id":27,"doc_module":4,"doc_module_name":44,"category_name":126,"show_sort_weight":27,"slug":127},"World Cup","world-cup",{"id":129,"doc_module":4,"doc_module_name":44,"category_name":130,"show_sort_weight":129,"slug":131},10,"Lifestyle","lifestyle",{"id":133,"doc_module":4,"doc_module_name":44,"category_name":134,"show_sort_weight":104,"slug":135},19,"General","general"]