[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83912-en":3,"doc-seo-83912-105":28,"detail-sidebar-cat-0-en-105":90},{"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":20,"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},83912,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Geometry-Aware Visual Odometry for Bronchoscopic Navigation via High-Gain Observer Fusion","Navigational bronchoscopy enables pulmonary interventions, yet conventional platforms rely on pre-operative CT or external sensors, restricting use in critical care and resource-limited settings. Vision-only navigation faces frequent VO failures and drift due to texture-poor airway imagery, specularities, and tubular anatomy vanishing-point singularities. A geometry-aware VO framework extracts vanishing-point cues from airway lumens, back-projects detected lumens to 3D rays, fuses them into stable heading, and combines looming-based velocity with VO using a high-gain observer enforcing airway-following priors. Validation on ex-vivo ventilated human lungs shows over 50% reduction in absolute trajectory error and lowest relative pose error versus leading baselines.","Geometry-Aware Visual Odometry for Bronchoscopic Navigation via  \nHigh-Gain Observer Fusion  \nMohammadreza Kasaei 1 ,2 , Francis Xiatian Zhang2 , Feng Li2 , Farshid Alambeigi3 , Kevin Dhaliwal2 , Mohsen Khadem 1 ,2  \narXiv :2607 .05 162v 1 [ cs .RO] 6 Jul 2026  \nAbstract—Navigational bronchoscopy is critical for pulmonary interventions, yet current platforms depend heavily on pre-operative CT or external sensors, limiting their use in critical care and resource-constrained settings. Vision-only navigation offers a scalable alternative, but conventional visual odometry (VO) struggles with texture-poor airway images, specularities, and the vanishing-point singularities of tubular anatomy, leading to frequent tracking failures and drift. We present a geometry-aware VO framework that explicitly leverages vanishing-point cues from airway lumens. Detected lumens are back-projected to 3D rays, whose weighted fusion yields a stable forward heading even when parallax cues are absent. This heading, together with looming-based velocity estimates, is fused with noisy VO outputs using a bespoke high-gain observer that enforces airway-following priors and rejects drift. We validate the method on ex-vivo mechanically ventilated human lungs with electromagnetic tracking ground truth. Compared to state-of-the-art pipelines (ORB-SLAM2, LoFTR-VO, DPVO), our approach reduces absolute trajectory error by more than 50% and achieves the lowest relative pose error across all test sequences.  \nI. INTRODUCTION  \nNavigational bronchoscopy is widely used for lung cancer diagnosis and pulmonary interventions. Commercial systems range from manual platforms such as superDimension (Medtronic) [1] to robotic solutions including Ion (Intuitive Surgical) [2], Monarch (J&J) [3], and Galaxy (Noah Medical) [4] . These platforms integrate electromagnetic (EM)  \n[5] or optical shape sensing [2] with pre-operative CT to register the bronchoscope within a 3D airway map, enabling precise guidance while reducing risks such as pneumothorax and hemorrhage [6] . Despite their success, sensor-based systems require specialised infrastructure (e.g., EM tracking, fluoroscopy), while CT-guided navigation is unsuitable for many critical care patients where high-quality scans are not feasible [7,8] . Consequently, NB is largely limited to elective cancer diagnostics. Moreover, CT-based registration is errorprone due to respiratory motion, with bronchial tree shifting up to 25 mm per cycle [9] .  \nAn alternative is Virtual Bronchoscopy (VB), where CTderived virtual images are matched to live video [10,11] . Although commercial VB exists, systems are semi-automatic, require operator input, and degrade under axial rotations [12] . Improvements include handcrafted registration [13–15], deep learning [16,17], and more recently view-synthesis with  \n1 School of Informatics, University of Edinburgh, UK.  \n2Baillie Gifford Pandemic Science Hub, Institute for Regeneration and Repair, University of Edinburgh, UK.  \n3Walker Department of Mechanical Engineering and Texas Robotics, The University of Texas at Austin, USA.  \nFig. 1: Vanishing-point geometry in bronchoscopy. The bronchoscope tip is steered by twist ϕ and bend θ, but in tubular airways these motions produce little parallax and camera singularities that make direct orientation recovery unreliable. Distal lumen entrances, however, act as portals aligned with the true bronchial axis. By back-projecting their centers to 3D rays (blue arrows) and averaging them, we obtain a stable forward heading (red arrow) that serves as a geometry-aware orientation prior even when classical VO cues are weak or absent.  \nNeRF, which aligns real video to CT-trained radiance fields [18] . Tian et al. [19] further proposed PANS, combining monocular depth-based motion inference with CT-informed airway semantics in a Monte Carlo framework for real-time robust localisation. Nevertheless, all CT-dependent methods remain constrained by the limitations of pr","cbCaikqSb3sFXpYU","https://ap.wps.com/l/cbCaikqSb3sFXpYU","pdf",4833002,1,"English","en",105,"# Abstract\n# Introduction\n## Limits of CT- and sensor-based navigation\n## Virtual bronchoscopy and registration constraints\n## Vision-based VO/SLAM challenges in bronchoscopy\n## Related work and recent progress","[{\"question\":\"Why do CT- and sensor-based navigational bronchoscopy systems limit use in critical care?\",\"answer\":\"They require specialized infrastructure such as electromagnetic tracking or rely on pre-operative CT, which may be infeasible for many patients in intensive care and can be unreliable due to respiratory motion.\"},{\"question\":\"What problem does conventional visual odometry face in bronchoscopic videos?\",\"answer\":\"Texture-poor, repetitive airway imagery and strong lighting effects (specularities, motion blur, illumination changes) weaken stable visual features, while tubular anatomy introduces vanishing-point singularities that cause tracking failures and drift.\"},{\"question\":\"How does the proposed geometry-aware VO framework improve tracking reliability?\",\"answer\":\"It leverages vanishing-point cues by back-projecting detected airway lumens into 3D rays, fusing them into a stable forward heading, then fuses this heading and looming-based velocity with noisy VO using a high-gain observer that enforces airway-following priors and rejects drift.\"}]",1784191402,20,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":26},"geometry-aware-visual-odometry-for-bronchoscopic-navigation-via-high-gain-observer-fusion","",{"@graph":34,"@context":84},[35,52,67],{"@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/geometry-aware-visual-odometry-for-bronchoscopic-navigation-via-high-gain-observer-fusion/83912/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why do CT- and sensor-based navigational bronchoscopy systems limit use in critical care?","Question",{"text":74,"@type":75},"They require specialized infrastructure such as electromagnetic tracking or rely on pre-operative CT, which may be infeasible for many patients in intensive care and can be unreliable due to respiratory motion.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What problem does conventional visual odometry face in bronchoscopic videos?",{"text":79,"@type":75},"Texture-poor, repetitive airway imagery and strong lighting effects (specularities, motion blur, illumination changes) weaken stable visual features, while tubular anatomy introduces vanishing-point singularities that cause tracking failures and drift.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the proposed geometry-aware VO framework improve tracking reliability?",{"text":83,"@type":75},"It leverages vanishing-point cues by back-projecting detected airway lumens into 3D rays, fusing them into a stable forward heading, then fuses this heading and looming-based velocity with noisy VO using a high-gain observer that enforces airway-following priors and rejects drift.","https://schema.org",{"og:url":50,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":44,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":44,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":44,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":44,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":44,"category_name":124,"show_sort_weight":27,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":27,"doc_module":4,"doc_module_name":44,"category_name":127,"show_sort_weight":27,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":44,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":44,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]