[{"data":1,"prerenderedAt":217},["ShallowReactive",2],{"method-schaub2022pc2bim":3},{"method":4,"reference":48,"equipment":69,"figures":100,"results":101},{"id":5,"label":6,"shortName":7,"title":8,"year":9,"era":10,"cluster":11,"scope":12,"keyIdeaZh":13,"keyIdeaEn":14,"fulltextStatus":15,"publicationStatus":16,"recommendation":17,"constructionRelevance":18,"validationEnvironment":19,"strengths":21,"limitations":26,"sensors":32,"platform":34,"estimator":37,"association":38,"timeModel":39,"deskew":39,"loopClosure":40,"globalOptimization":41,"mapRepresentation":42,"prior":43,"outputGeometry":44,"compute":45,"codeUrl":46,"codeLicense":41,"relatedVersions":47},"schaub2022pc2bim","Schaub et al., 2022","Point cloud to BIM registration (SLAM tracking)","Point cloud to BIM registration for robot localization and Augmented Reality",2022,"recent","C11b","localization_in_prior_map_or_bim","作者以 Kudan LiDAR SLAM 追蹤 Ouster OS0-128 光達（含感測器 IMU 資料），將關鍵影格累積的點雲配準到以 IfcOpenShell 解析並體素化（0.1 m）的 BIM 點雲：先以法向量角度直方圖做軸向對齊，再以只保留垂直於投影面點的法向過濾樣板匹配（每 1° 測試）粗對位，最後以隨機子取樣 ICP 精對位，得到感測器在 BIM 座標中的位姿，供擴增實境檢查與 Boston Dynamics Spot 遠端操作使用。評估只用手持錄製資料，且以每段錄製起點人工量測的初始位置作為唯一參考：28 m 走廊（只含走廊的 BIM）各關鍵影格中位數平均 XY 誤差 0.03 m、Z 0.035 m，全部成功；TU Wien 圖書館六樓含多個相似房間的環形走廊，前 10 個關鍵影格成功率只有 30%，到第 36 個關鍵影格前平均 XY 0.19 m、Z 0.24 m，之後 XY 低於 0.3 m、Z 低於 0.4 m。誤差同時包含配準誤差與 SLAM 漂移。","Registers a Kudan-SLAM keyframe map from an Ouster OS0-128 to a voxelized IFC model (axis alignment, normal-filtered template matching, ICP); against hand-measured start positions it reaches 0.03 m (median XY) with a hallway-only BIM, but on a self-similar library floor succeeds only 30% of the time in the first keyframes and averages 0.19 m XY and 0.24 m Z, with drift pushing errors toward 0.3-0.4 m.","full_text_reviewed","peer_reviewed_published","supplementary","應用動機為建築進度控制、數位輔助維護與遠端巡檢；測試在 TU Wien 研究室旁約 28 m 長、2.5 m 寬的走廊，以及 TU Wien 圖書館六樓的環形走廊進行，兩者都是既有建築；圖書館樓層可見 BIM 未記載的家具、植物與牆體、門窗差異，且無法進入個別房間；非施工中工地（Sec. 1、4.2、5）。",[20],"completed_building",[22,23,24,25],"env. 1 (28 m x 2.5 m hallway, hallway-only BIM): XY error 0.03 m and Z 0.035 m (medians averaged over keyframes); registration successful at all keyframes of 10 recordings (Sec. 4.3)","env. 2: registration virtually always successful from keyframe 28; mean XY 0.19 m and Z 0.24 m up to keyframe 36 (Sec. 4.3)","supports non-perpendicular walls and varying floor levels, unlike Herbers and Konig (Sec. 5)","registration runs in the background without degrading live tracking (Sec. 4.3)",[27,28,29,30,31],"self-similar floor plan causes wrong template matches for up to 20 first keyframes; success only 30% in keyframes 2-10 and 50-90% in keyframes 12-26 (Sec. 4.3, 5)","error grows with accumulated SLAM drift, notably after keyframe 38 (about 60.8 m); afterwards XY below 0.3 m and Z below 0.4 m (Sec. 4.3)","ground truth only for the initial sensor position, measured manually; SLAM drift contribution not quantified (Sec. 4.1)","differences between BIM and building (furniture, plants, missing or extra walls, doors, windows) hamper registration (Sec. 5)","only corridors on one floor recorded; rooms not accessible (Sec. 4.2)",[33],"Ouster OS0-128 Gen 2 LiDAR (128 channels, 90 deg VFOV; 512x20 in env. 1, 1024x20 in env. 2; up to 131,072 points per frame) with IMU data from the sensor",[35,36],"handheld: custom wooden frame with dual hold and 24 V battery (all evaluation recordings)","legged robot Boston Dynamics Spot (demonstration setup, not evaluated)","Kudan LiDAR SLAM (commercial SDK; tracking voxel 0.25 m) for pose tracking; point cloud to BIM registration of the accumulated keyframe map gives the SLAM-to-BIM transform, repeatable when drift grows","PCA normals and normal-angle histograms for axis alignment; normal-filtered template matching (points kept only when the dot product of point normal and plane normal is at most 0.1): rotation from XY projections tested at each 1 deg, first at lower resolution and then at the 0.1 m resolution, height matched with projections along the X and Y axes; ICP with random sub-sampling, 100 iterations split into 10 random 10% subsets","not_reported","may occur inside Kudan SLAM, but neither loop-closure accuracy nor its influence on registration was evaluated","not_verified","keyframe-accumulated LiDAR point cloud from Kudan SLAM; BIM converted to a voxel point cloud (0.1 m) with IfcOpenShell and the Voxelization Toolkit for one manually selected floor (env. 2 floor: 1,035,690 points)","BIM (IFC) of the relevant floor, selected manually; hallway BIM derived from a high-resolution scan, library BIM from 2D floor plans and facade photogrammetry","sensor pose in BIM frame","handheld: all components on a Razer Blade 15 laptop (11th Gen Intel Core i7, 8 cores, 32 GB RAM, NVIDIA GeForce RTX 3080, Windows 11); robot: tracking on an Intel NUC (Core i7, 4 cores, 16 GB RAM, Windows 10), localization and visualization on the laptop over WiFi; registration time split 2% axis alignment, 58% template matching, 40% ICP",null,[],{"id":5,"kind":49,"shortName":7,"title":8,"authors":50,"year":9,"venue":55,"venueType":56,"publisher":57,"volumeIssuePages":58,"doi":59,"arxivId":46,"url":60,"firstPublicDate":61,"publicationStatus":16,"metadataStatus":62,"fulltextStatus":15,"era":10,"classicReason":63,"codeUrl":46,"cluster":11,"topics":64,"mdpi":65,"verification":66,"label":6,"fulltextRoute":67,"versionRead":68,"addedByCensus":65},"method",[51,52,53,54],"Linus Schaub","Iana Podkosova","Christian Schonauer","Hannes Kaufmann","2022 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","conference","IEEE","77-84","10.1109\u002Fismar-adjunct57072.2022.00025","https:\u002F\u002Fapi.openalex.org\u002Fworks\u002Fdoi:10.1109\u002Fismar-adjunct57072.2022.00025","2022-10","metadata_verified","not_applicable",[11],false,"confirmed","NTU institutional (Chrome)","version of record, ISMAR-Adjunct 2022, pp. 77-84, IEEE Xplore HTML (document 9974380; conference 17-21 Oct 2022, Singapore; added to Xplore 15 Dec 2022); author version on Zenodo record 7986942 (labelled Preprint, deposited 2023-05-30) also read, text identical in all sections",[70,77,82,87,91,97],{"category":71,"model":72,"canonical":73,"role":74,"dataset":46,"specs":75,"locator":76},"lidar","Ouster OS0-128 Gen 2","Ouster OS0-128","method input","128 channels, 90 deg vertical FOV; resolution 512x20 (env. 1) or 1024x20 (env. 2); up to 131,072 points per frame; raw data recorded as .pcap with Ouster Studio","Sec. 3.3, 4.1, 4.3",{"category":78,"model":79,"canonical":79,"role":74,"dataset":46,"specs":80,"locator":81},"imu","IMU of the Ouster OS0-128 (model not reported)","IMU data from the LiDAR sensor fed to SLAM tracking","Sec. 3.1",{"category":83,"model":84,"canonical":84,"role":74,"dataset":46,"specs":85,"locator":86},"platform","custom-built wooden handheld frame with dual hold","24 V battery; Ethernet to laptop; used for all evaluation recordings","Sec. 3.3, Fig. 5",{"category":83,"model":88,"canonical":88,"role":74,"dataset":46,"specs":89,"locator":90},"Boston Dynamics Spot","LiDAR and payload computer powered by the robot; demonstration only","Sec. 3.3, Figs. 1, 5",{"category":92,"model":93,"canonical":93,"role":94,"dataset":46,"specs":95,"locator":96},"compute","Intel NUC (payload computer on Spot)","compute for runtime","Intel Core i7 CPU (4 cores), 16 GB RAM, Windows 10; runs the real-time data and tracking component","Sec. 3.3",{"category":92,"model":98,"canonical":98,"role":94,"dataset":46,"specs":99,"locator":96},"Razer Blade 15","11th Gen Intel Core i7 (8 cores), 32 GB RAM, NVIDIA GeForce RTX 3080, Windows 11; runs all components in the handheld setup and localization plus visualization in the robot setup",[],{"totalRows":102,"groupCount":103,"groups":104,"others":216},9,2,[105,193],{"slug":106,"group":107,"sourceId":5,"sourceLabel":6,"table":108,"selfRows":109,"metrics":110,"seqs":132,"entrants":153,"cells":157,"outcomes":182,"locators":183,"hardware":187,"wordings":188,"notes":189},"schaub2022pc2bim-text-sec-4-3","schaub2022pc2bim:Text Sec.4.3","Text Sec.4.3",8,[111,116,118,121,123,126,128,130],{"label":112,"unit":113,"statistic":114,"alignment":115},"XY error averaged over all keyframes","m","median","none",{"label":117,"unit":113,"statistic":114,"alignment":115},"Z error averaged over all keyframes",{"label":119,"unit":120,"statistic":39,"alignment":115},"registration successful for all keyframes in all cases","%",{"label":122,"unit":120,"statistic":39,"alignment":115},"registration success rate",{"label":124,"unit":113,"statistic":125,"alignment":115},"XY error averaged over all keyframes up to 36","mean",{"label":127,"unit":113,"statistic":125,"alignment":115},"Z error averaged over all keyframes up to 36",{"label":129,"unit":113,"statistic":39,"alignment":115},"mean localization error (Fig. 10 curve) stays below this bound in the XY plane, as stated in the text",{"label":131,"unit":113,"statistic":39,"alignment":115},"mean localization error (Fig. 10 curve) stays below this bound along the Z axis, as stated in the text",[133,137,139,141,145,147,149,151],{"dataset":134,"sequence":135,"environment":136},"TU Wien hallway (test environment 1)","10 recordings, keyframes 1-9 (mean 21.5 m travelled at keyframe 9)","28 m x 2.5 m hallway, hallway-only BIM",{"dataset":134,"sequence":138,"environment":136},"10 recordings, keyframes 1-9",{"dataset":134,"sequence":140,"environment":136},"10 recordings, all analysed keyframes",{"dataset":142,"sequence":143,"environment":144},"TU Wien library, 6th floor (test environment 2)","keyframes 2-10","corridor loop with self-similar rooms and non-perpendicular walls",{"dataset":142,"sequence":146,"environment":144},"keyframes up to 36 (keyframe 38 = 60.8 m on average)",{"dataset":142,"sequence":148,"environment":144},"keyframes up to 36",{"dataset":142,"sequence":150,"environment":144},"keyframes after 36 up to 60 (85-130 m travelled at keyframes 54-60)",{"dataset":142,"sequence":152,"environment":144},"keyframes after 36 up to 60",[154],{"name":155,"methodId":5,"linkable":156,"proposed":156,"self":156},"Kudan SLAM + point cloud to BIM registration (proposed)",true,[158,162,165,167,170,173,176,179],[159,159,159,160,161,159,161,161,159],0,0.03,-1,[159,163,163,164,161,159,161,161,159],1,0.035,[159,103,103,166,161,163,161,161,163],100,[159,168,168,169,161,163,161,161,103],3,30,[159,171,171,172,161,103,161,161,103],4,0.19,[159,174,174,175,161,103,161,161,103],5,0.24,[159,177,177,178,161,103,161,161,103],6,0.3,[159,180,180,181,161,103,161,161,103],7,0.4,[],[184,185,186],"Sec. 4.3, Fig. 9","Sec. 4.3","Sec. 4.3, Fig. 10",[],[],[190,191,192],"Localization error = registration-derived initial sensor position vs manually measured initial position in the BIM frame, evaluated at every second keyframe; env. 1 reports medians averaged over keyframes; 10 handheld recordings, 512x20.","Success = localization error below 1 m.","Env. 2: partial scans of the sixth floor registered to the BIM of the whole floor; 10 handheld recordings starting in areas A1-A5, 1024x20; means averaged over keyframes; success = error below 1 m.",{"slug":194,"group":195,"sourceId":5,"sourceLabel":6,"table":196,"selfRows":163,"metrics":197,"seqs":200,"entrants":204,"cells":206,"outcomes":209,"locators":210,"hardware":212,"wordings":213,"notes":214},"schaub2022pc2bim-text-sec-5","schaub2022pc2bim:Text Sec.5","Text Sec.5",[198],{"label":199,"unit":113,"statistic":125,"alignment":115},"average Z-axis accuracy at the best interval",[201],{"dataset":142,"sequence":202,"environment":203},"keyframes 20-38","corridor loop with self-similar rooms",[205],{"name":155,"methodId":5,"linkable":156,"proposed":156,"self":156},[207],[159,159,159,208,161,159,161,161,159],0.25,[],[211],"Sec. 5",[],[],[215],"Best interval in env. 2: after keyframe 20 (about 25 m) and before keyframe 38 (about 60 m); average values.",[],1790510659425]