[{"data":1,"prerenderedAt":490},["ShallowReactive",2],{"method-ndtloam2022":3},{"method":4,"reference":54,"equipment":80,"figures":120,"results":121},{"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":22,"limitations":28,"sensors":34,"platform":36,"estimator":39,"association":40,"timeModel":41,"deskew":42,"loopClosure":43,"globalOptimization":44,"mapRepresentation":45,"prior":44,"outputGeometry":46,"compute":47,"codeUrl":48,"codeLicense":49,"relatedVersions":50},"ndtloam2022","Chen et al., 2022b","NDT-LOAM","NDT-LOAM: A Real-Time Lidar Odometry and Mapping With Weighted NDT and LFA",2022,"recent","C04","odometry_with_local_mapping","NDT-LOAM 把 LOAM 的特徵式前端改成加權的常態分布轉換（NDT）直接配準：每個 NDT 格依量測距離與格內形狀（平面、線狀或立體）給不同權重，並以目前幀對最近關鍵影格配準（Scan2Key）降低逐幀累積誤差。得到的初始位姿再交給沿用 LOAM 建圖模組的局部特徵調整（LFA），以角點與平面點對局部地圖精修。系統只處理前端，沒有迴圈閉合；在 KITTI 上平均平移漂移為 0.899%。","LOAM variant whose odometry front end is a range- and planarity-weighted NDT registered scan-to-keyframe, followed by LOAM-style local feature adjustment against a local map; front end only, 0.899% average KITTI drift at about 10 Hz.","full_text_reviewed","peer_reviewed_published","background","論文未在施工現場測試；以 Kylin 背包在室內及室內外混合路線（含上下樓梯）測試，屬既有建築環境，但只以起訖點偏移估計誤差。依距離與平面性為 NDT 格加權的做法，可能有利於樓板與牆面等平面為主的建築場景，這屬推論。",[20,21],"public_benchmark","completed_building",[23,24,25,26,27],"Average KITTI 00-10 translational error 0.899% after LFA, versus 1.809% for A-LOAM and 1.27% for F-LOAM, and at the level of the LOAM paper values (Table II)","Weighted NDT lowers odometry error by about 12% relative to classic NDT (1.041% to 0.910% with Scan2Key) and Scan2Key roughly halves the error of Scan2Scan (Sec. IV-A)","Odometry-only initial pose error 0.910% versus 4.913% for the A-LOAM odometry (Table I)","Kylin backpack indoor and indoor-outdoor runs: start-to-end error 0.20 m and 0.25 m versus 7.99 m and 2.60 m for LeGO-LOAM (Table IV)","APE RMSE on KITTI 00, 05 and 09 of 3.98, 2.39 and 1.58 m versus 5.98, 2.97 and 2.30 m for LeGO-LOAM with loop closure; the authors describe this as almost 50% better (Table III; Sec. IV-C)",[29,30,31,32,33],"No loop closure or back-end optimization (Sec. V)","Accuracy is poorer on KITTI 01, 02, 08 and 10 (above 1.0%), attributed to highway speed and few features, calibration of the sensors, ground-truth error at the start of 08 and vibration on rough roads (Sec. IV-C)","NDT cell weights (1.25, 1.0, 0.75) were set empirically (Sec. III-B)","Backpack evaluation uses only the start-to-end offset because no GPS ground truth was available (Sec. IV-D)","LOAM results are copied from its original paper rather than rerun (Sec. IV-C)",[35],"3D LiDAR only (Velodyne HDL-64E in KITTI; horizontal Velodyne VLP-16 on the Kylin backpack)",[37,38],"vehicle (KITTI)","backpack (Kylin)","two stages: direct odometry by weighted NDT solved with Newton's method and line search against a keyframe (Scan2Key), then local feature adjustment (LFA) that reuses the LOAM mapping module to refine the pose with corner and surface feature residuals against a local map, two iterations (Sec. III)","NDT cells (1 m grid in KITTI tests) weighted by point range and by cell dimensionality from covariance eigenvalues (planar 1.25, volumetric 1.0, linear 0.75); LFA corner and surface correspondences searched in a KD-tree built from map cubes intersecting the scan (Sec. III-B; Sec. III-D; Sec. IV-A)","discrete poses","not described","none (loop closure and graph optimization are named as future work) (Sec. III-C; Sec. V)","none","LOAM-style corner and surface feature map stored in cubic areas for LFA; keyframe scans (selected by 10 m, 10 deg or 1 s on KITTI; 2 m or 10 deg on the backpack) as NDT targets (Sec. III-C; Sec. III-D; Sec. IV-A; Sec. IV-D)","trajectory and 3D point cloud map (Figs. 5 and 7)","laptop Intel i7-7700HQ at 2.8 GHz with 8 GB RAM, ROS on Ubuntu 16.04; reported as real time at 10 Hz; per-scan module times on KITTI of 38.0-48.2 ms (NDT odometry), 37.1-42.9 ms (LFA extraction) and 86.9-107.8 ms (LFA mapping) (abstract; Sec. IV; Table V)","https:\u002F\u002Fgithub.com\u002FBurryChen\u002Flv_slam","not stated (no LICENSE file at the repository root)",[51],{"relation":52,"title":53,"doi_or_url":48},"code_release","BurryChen\u002Flv_slam (named in the paper abstract)",{"id":5,"kind":55,"shortName":7,"title":8,"authors":56,"year":9,"venue":64,"venueType":65,"publisher":66,"volumeIssuePages":67,"doi":68,"arxivId":69,"url":70,"firstPublicDate":71,"publicationStatus":16,"metadataStatus":72,"fulltextStatus":15,"era":10,"classicReason":73,"codeUrl":48,"cluster":11,"topics":74,"mdpi":75,"verification":76,"label":6,"fulltextRoute":77,"versionRead":78,"addedByCensus":79},"method",[57,58,59,60,61,62,63],"Shoubin Chen","Hao Ma","Changhui Jiang","Baoding Zhou","Weixing Xue","Zhenzhong Xiao","Qingquan Li","IEEE Sensors Journal","journal","IEEE","22(4):3660-3671","10.1109\u002Fjsen.2021.3135055",null,"https:\u002F\u002Fdoi.org\u002F10.1109\u002FJSEN.2021.3135055","2021-12-28","metadata_verified","not_applicable",[11],false,"corrected","NTU institutional (Chrome)","IEEE Xplore version of record (HTML full text; tables read from the published table images)",true,[81,88,93,97,103,107,111,115],{"category":82,"model":83,"canonical":83,"role":84,"dataset":85,"specs":86,"locator":87},"lidar","Velodyne HDL-64E","dataset sensor","KITTI odometry","KITTI recording platform; only the Velodyne data are used","Sec. IV; Fig. 2",{"category":89,"model":90,"canonical":90,"role":91,"dataset":85,"specs":92,"locator":87},"gnss","OXTS RT 3003","reference or ground truth","high-accuracy GPS\u002FINS localization system providing ground truth",{"category":94,"model":95,"canonical":95,"role":84,"dataset":85,"specs":96,"locator":87},"stereo_camera","four stereo camera systems (grayscale and color)","KITTI platform cameras; not used by the method",{"category":82,"model":98,"canonical":98,"role":99,"dataset":100,"specs":101,"locator":102},"Velodyne VLP-16","method input","Kylin backpack sequences K1 and K2","two lidars on the backpack; only the horizontal one used; 10 Hz","Sec. IV; Sec. IV-D",{"category":94,"model":104,"canonical":104,"role":84,"dataset":100,"specs":105,"locator":106},"Mynak D1000-IR-120 color binocular camera","left camera images at 640 x 480 used in the experiment (their role is not stated)","Sec. IV",{"category":108,"model":109,"canonical":109,"role":84,"dataset":100,"specs":110,"locator":106},"imu","Xsens-300","on the backpack; use by the method not stated",{"category":112,"model":113,"canonical":113,"role":99,"dataset":100,"specs":114,"locator":87},"platform","Kylin backpack","walked at about 1 m\u002Fs; no GPS device",{"category":116,"model":117,"canonical":117,"role":118,"dataset":69,"specs":119,"locator":106},"compute","Intel i7-7700HQ","compute for runtime","laptop CPU at 2.8 GHz, 8 GB RAM, ROS on Ubuntu 16.04",[],{"totalRows":122,"groupCount":123,"groups":124,"others":479},54,6,[125,202,299,416],{"slug":126,"group":127,"sourceId":5,"sourceLabel":6,"table":128,"selfRows":129,"metrics":130,"seqs":139,"entrants":152,"cells":159,"outcomes":195,"locators":196,"hardware":197,"wordings":199,"notes":200},"ndtloam2022-table-v","ndtloam2022:Table V","Table V",15,[131,135,137],{"label":132,"unit":133,"statistic":134,"alignment":73},"DLO time per scan (ms)","ms","not_reported",{"label":136,"unit":133,"statistic":134,"alignment":73},"LFA-Extraction time per scan (ms)",{"label":138,"unit":133,"statistic":134,"alignment":73},"LFA-Mapping time per scan (ms)",[140,143,145,147,149],{"dataset":85,"sequence":141,"environment":142},"#04","vehicle, road",{"dataset":85,"sequence":144,"environment":142},"#06",{"dataset":85,"sequence":146,"environment":142},"#07",{"dataset":85,"sequence":148,"environment":142},"#09",{"dataset":113,"sequence":150,"environment":151},"K1","backpack, indoor",[153,155,157],{"name":154,"methodId":5,"linkable":79,"proposed":79,"self":79},"NDT-LOAM DLO",{"name":156,"methodId":5,"linkable":79,"proposed":79,"self":79},"NDT-LOAM LFA-Extraction",{"name":158,"methodId":5,"linkable":79,"proposed":79,"self":79},"NDT-LOAM LFA-Mapping",[160,164,167,170,172,173,175,177,179,181,184,186,188,191,193],[161,161,161,162,163,161,161,163,161],0,48.2,-1,[165,165,161,166,163,161,161,163,161],1,42.9,[168,168,161,169,163,161,161,163,161],2,86.9,[161,161,165,171,163,161,161,163,161],46.8,[165,165,165,166,163,161,161,163,161],[168,168,165,174,163,161,161,163,161],107.8,[161,161,168,176,163,161,161,163,161],38,[165,165,168,178,163,161,161,163,161],37.1,[168,168,168,180,163,161,161,163,161],89.8,[161,161,182,183,163,161,161,163,161],3,44.5,[165,165,182,185,163,161,161,163,161],40.6,[168,168,182,187,163,161,161,163,161],90.2,[161,161,189,190,163,161,161,163,161],4,9.9,[165,165,189,192,163,161,161,163,161],12.1,[168,168,189,194,163,161,161,163,161],103.7,[],[128],[198],"laptop Intel i7-7700HQ 2.8 GHz, 8 GB RAM",[],[201],"Runtime of modules for processing one scan (ms) on KITTI 04, 06, 07, 09 and backpack K1",{"slug":203,"group":204,"sourceId":5,"sourceLabel":6,"table":205,"selfRows":206,"metrics":207,"seqs":212,"entrants":233,"cells":239,"outcomes":293,"locators":294,"hardware":295,"wordings":296,"notes":297},"ndtloam2022-table-i","ndtloam2022:Table I","Table I",12,[208],{"label":209,"unit":210,"statistic":211,"alignment":73},"position error (%)","%","mean",[213,215,217,219,221,222,224,225,226,228,229,231],{"dataset":85,"sequence":214,"environment":142},"#00",{"dataset":85,"sequence":216,"environment":142},"#01",{"dataset":85,"sequence":218,"environment":142},"#02",{"dataset":85,"sequence":220,"environment":142},"#03",{"dataset":85,"sequence":141,"environment":142},{"dataset":85,"sequence":223,"environment":142},"#05",{"dataset":85,"sequence":144,"environment":142},{"dataset":85,"sequence":146,"environment":142},{"dataset":85,"sequence":227,"environment":142},"#08",{"dataset":85,"sequence":148,"environment":142},{"dataset":85,"sequence":230,"environment":142},"#10",{"dataset":85,"sequence":232,"environment":142},"Average",[234,237],{"name":235,"methodId":236,"linkable":79,"proposed":75,"self":75},"ALOAM (odometry only)","aloam_software",{"name":238,"methodId":5,"linkable":79,"proposed":79,"self":79},"NDT-LOAM (odometry only, wNDT + Scan2Key)",[240,242,244,246,248,250,253,255,258,261,264,267,270,272,274,276,278,280,282,284,285,287,289,291],[161,161,161,241,163,161,163,163,161],4.12,[161,161,165,243,163,161,163,163,161],3.44,[161,161,168,245,163,161,163,163,161],7.35,[161,161,182,247,163,161,163,163,161],3.04,[161,161,189,249,163,161,163,163,161],0.69,[161,161,251,252,163,161,163,163,161],5,4.29,[161,161,123,254,163,161,163,163,161],0.99,[161,161,256,257,163,161,163,163,161],7,2.24,[161,161,259,260,163,161,163,163,161],8,4.89,[161,161,262,263,163,161,163,163,161],9,6.06,[161,161,265,266,163,161,163,163,161],10,3.63,[161,161,268,269,163,161,163,163,161],11,4.913,[165,161,161,271,163,161,163,163,161],0.76,[165,161,165,273,163,161,163,163,161],2.25,[165,161,168,275,163,161,163,163,161],1.03,[165,161,182,277,163,161,163,163,161],0.65,[165,161,189,279,163,161,163,163,161],0.34,[165,161,251,281,163,161,163,163,161],0.67,[165,161,123,283,163,161,163,163,161],0.41,[165,161,256,279,163,161,163,163,161],[165,161,259,286,163,161,163,163,161],0.9,[165,161,262,288,163,161,163,163,161],0.88,[165,161,265,290,163,161,163,163,161],1.12,[165,161,268,292,163,161,163,163,161],0.91,[],[205],[],[],[298],"KITTI 00-10, odometry part only (initial pose): A-LOAM feature odometry versus NDT-LOAM weighted NDT with Scan2Key; position error (%) from the KITTI development kit",{"slug":300,"group":301,"sourceId":5,"sourceLabel":6,"table":302,"selfRows":206,"metrics":303,"seqs":305,"entrants":318,"cells":328,"outcomes":410,"locators":411,"hardware":412,"wordings":413,"notes":414},"ndtloam2022-table-ii","ndtloam2022:Table II","Table II",[304],{"label":209,"unit":210,"statistic":211,"alignment":73},[306,307,308,309,310,311,312,313,314,315,316,317],{"dataset":85,"sequence":214,"environment":142},{"dataset":85,"sequence":216,"environment":142},{"dataset":85,"sequence":218,"environment":142},{"dataset":85,"sequence":220,"environment":142},{"dataset":85,"sequence":141,"environment":142},{"dataset":85,"sequence":223,"environment":142},{"dataset":85,"sequence":144,"environment":142},{"dataset":85,"sequence":146,"environment":142},{"dataset":85,"sequence":227,"environment":142},{"dataset":85,"sequence":148,"environment":142},{"dataset":85,"sequence":230,"environment":142},{"dataset":85,"sequence":232,"environment":142},[319,321,324,327],{"name":320,"methodId":236,"linkable":79,"proposed":75,"self":75},"ALOAM",{"name":322,"methodId":323,"linkable":79,"proposed":75,"self":75},"FLOAM [36]","floam2021",{"name":325,"methodId":326,"linkable":79,"proposed":75,"self":75},"LOAM (from original paper)","loam2017_auro",{"name":7,"methodId":5,"linkable":79,"proposed":79,"self":79},[329,330,332,334,335,337,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,378,379,381,383,385,386,388,389,391,392,393,395,396,397,399,400,401,403,405,407,408],[161,161,161,288,163,161,163,163,161],[161,161,165,331,163,161,163,163,161],2.09,[161,161,168,333,163,161,163,163,161],4.67,[161,161,182,281,163,161,163,163,161],[161,161,189,336,163,161,163,163,161],0.33,[161,161,251,338,163,161,163,163,161],0.53,[161,161,123,340,163,161,163,163,161],0.56,[161,161,256,342,163,161,163,163,161],0.32,[161,161,259,344,163,161,163,163,161],1.05,[161,161,262,346,163,161,163,163,161],0.8,[161,161,265,348,163,161,163,163,161],1.17,[161,161,268,350,163,161,163,163,161],1.809,[165,161,161,352,163,161,163,163,161],0.92,[165,161,165,354,163,161,163,163,161],2.8,[165,161,168,356,163,161,163,163,161],1.56,[165,161,182,358,163,161,163,163,161],1.09,[165,161,189,360,163,161,163,163,161],1.43,[165,161,251,362,163,161,163,163,161],0.79,[165,161,123,364,163,161,163,163,161],0.72,[165,161,256,366,163,161,163,163,161],0.54,[165,161,259,368,163,161,163,163,161],1.11,[165,161,262,370,163,161,163,163,161],1.28,[165,161,265,372,163,161,163,163,161],1.77,[165,161,268,374,163,161,163,163,161],1.27,[168,161,161,376,163,161,163,163,161],0.78,[168,161,165,360,163,161,163,163,161],[168,161,168,352,163,161,163,163,161],[168,161,182,380,163,161,163,163,161],0.86,[168,161,189,382,163,161,163,163,161],0.71,[168,161,251,384,163,161,163,163,161],0.57,[168,161,123,277,163,161,163,163,161],[168,161,256,387,163,161,163,163,161],0.63,[168,161,259,290,163,161,163,163,161],[168,161,262,390,163,161,163,163,161],0.77,[168,161,265,362,163,161,163,163,161],[182,161,161,362,163,161,163,163,161],[182,161,165,394,163,161,163,163,161],1.46,[182,161,168,358,163,161,163,163,161],[182,161,182,277,163,161,163,163,161],[182,161,189,398,163,161,163,163,161],0.31,[182,161,251,366,163,161,163,163,161],[182,161,123,340,163,161,163,163,161],[182,161,256,402,163,161,163,163,161],0.27,[182,161,259,404,163,161,163,163,161],1.04,[182,161,262,406,163,161,163,163,161],0.74,[182,161,265,290,163,161,163,163,161],[182,161,268,409,163,161,163,163,161],0.899,[],[302],[],[],[415],"KITTI 00-10 after refinement (LFA); position error (%); A-LOAM and NDT-LOAM run at 10 Hz; LOAM values from the original LOAM paper (1 Hz); F-LOAM values from [36]",{"slug":417,"group":418,"sourceId":5,"sourceLabel":6,"table":419,"selfRows":262,"metrics":420,"seqs":430,"entrants":434,"cells":439,"outcomes":473,"locators":474,"hardware":475,"wordings":476,"notes":477},"ndtloam2022-table-iii","ndtloam2022:Table III","Table III",[421,424,427],{"label":422,"unit":423,"statistic":211,"alignment":134},"Absolute Pose Error, mean (m)","m",{"label":425,"unit":423,"statistic":426,"alignment":134},"Absolute Pose Error, std (m)","std",{"label":428,"unit":423,"statistic":429,"alignment":134},"Absolute Pose Error, RMSE (m)","RMSE",[431,432,433],{"dataset":85,"sequence":214,"environment":142},{"dataset":85,"sequence":223,"environment":142},{"dataset":85,"sequence":148,"environment":142},[435,438],{"name":436,"methodId":437,"linkable":79,"proposed":75,"self":75},"LeGO-LOAM","legoloam2018",{"name":7,"methodId":5,"linkable":79,"proposed":79,"self":79},[440,442,444,446,448,450,452,453,454,456,458,460,462,464,466,468,470,471],[161,161,161,441,163,161,163,163,161],5.16,[161,165,161,443,163,161,163,163,161],2.87,[161,168,161,445,163,161,163,163,161],5.98,[161,161,165,447,163,161,163,163,161],2.65,[161,165,165,449,163,161,163,163,161],1.34,[161,168,165,451,163,161,163,163,161],2.97,[161,161,168,168,163,161,163,163,161],[161,165,168,290,163,161,163,163,161],[161,168,168,455,163,161,163,163,161],2.3,[165,161,161,457,163,161,163,163,161],3.38,[165,165,161,459,163,161,163,163,161],1.97,[165,168,161,461,163,161,163,163,161],3.98,[165,161,165,463,163,161,163,163,161],1.99,[165,165,165,465,163,161,163,163,161],1.32,[165,168,165,467,163,161,163,163,161],2.39,[165,161,168,469,163,161,163,163,161],1.38,[165,165,168,376,163,161,163,163,161],[165,168,168,472,163,161,163,163,161],1.58,[],[419],[],[],[478],"KITTI 00, 05, 09; absolute pose error (m) computed with evo; LeGO-LOAM with loop closure; alignment not stated",[480,485],{"group":481,"slug":482,"sourceLabel":6,"table":483,"selfRows":189,"datasets":484},"ndtloam2022:Text Sec. IV-A","ndtloam2022-text-sec-iv-a","Text Sec. IV-A",[85],{"group":486,"slug":487,"sourceLabel":6,"table":488,"selfRows":168,"datasets":489},"ndtloam2022:Table IV","ndtloam2022-table-iv","Table IV",[113],1790510660770]