[{"data":1,"prerenderedAt":103},["ShallowReactive",2],{"method-ldso2018":3},{"method":4,"reference":60,"equipment":81,"figures":102,"results":86},{"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":32,"platform":34,"estimator":36,"association":37,"timeModel":38,"deskew":39,"loopClosure":40,"globalOptimization":41,"mapRepresentation":42,"prior":43,"outputGeometry":44,"compute":45,"codeUrl":46,"codeLicense":47,"relatedVersions":48},"ldso2018","Gao et al., 2018","LDSO","LDSO: Direct Sparse Odometry with Loop Closure",2018,"recent","C08","full_slam_with_global_correction","LDSO 把直接稀疏里程計 DSO 擴充為具迴圈閉合的單目視覺 SLAM。它保留 DSO 以梯度選點的直接法追蹤，但讓部分選點偏向可重複的角點，只在關鍵影格上計算 ORB 描述子並建立詞袋資料庫以偵測迴圈。迴圈候選以 ORB 匹配與 RANSAC PnP 初始化，再同時最小化三維點對齊與二維重投影誤差求 Sim(3) 相對位姿；這些約束與滑動視窗的共視相對位姿一起放入 Sim(3) 位姿圖，以 g2o 最佳化修正旋轉、平移與尺度漂移，不做全域光束法平差。","LDSO extends direct sparse odometry (DSO) to monocular SLAM by biasing point selection toward repeatable corners for bag-of-words loop detection, estimating Sim(3) loop constraints from combined 3D and 2D geometric errors, and correcting drift with a Sim(3) pose graph fused with DSO's co-visibility constraints.","full_text_reviewed","peer_reviewed_published","supplementary","論文未在營建工地測試；評估使用 TUM-Mono（室內外序列）、EuRoC MAV 與 KITTI Odometry 公開資料。直接法可利用白牆或弱紋理區的梯度，且迴圈閉合能修正單目尺度漂移，對低成本相機記錄施工進度有參考價值；但輸出僅為單目尺度的稀疏點雲，需外部尺度或感測器融合才能用於量測（推論）。",[20,21],"public_benchmark","independent_reference",[23,24,25,26,27],"Corner-biased point selection keeps DSO's odometry accuracy and robustness on TUM-Mono (Figs. 4-5; Sec. IV-A)","On KITTI sequences with loops LDSO sharply reduces DSO's ATE, for example 126.7 m to 9.322 m on seq. 00 and 49.85 m to 5.1 m on seq. 05 (Table I)","Accuracy comparable to ORB-SLAM2 on KITTI without global bundle adjustment, and it runs on seq. 01 where ORB-SLAM2 failed (Table I)","More robust than ORB-SLAM2 on EuRoC, though ORB-SLAM2 is more accurate there (Sec. IV-B; Figs. 8-9, plotted)","Descriptors are computed only for keyframes, keeping extra cost small (Sec. IV-D; Table II)",[29,30,31],"On KITTI seq. 08 the ATE stays large at 129.02 m, above DSO's 120.17 m","the paper names only seq. 00, 05 and 07 as sequences with loops (Sec. IV-C","Table I)",[33],"monocular camera",[35],"[\"TUM-Mono indoor and outdoor sequences (carrying mode not stated in the paper)\", \"EuRoC MAV sequences\", \"KITTI Odometry training sequences (platform not described in the paper)\"]","DSO sliding-window photometric bundle adjustment (5 to 7 active keyframes, inverse-depth points, affine brightness and exposure) as the odometry front end; back end Sim(3) pose graph built from co-visibility relative poses of the window plus loop constraints, optimised with g2o while the current window poses are kept fixed (Secs. III-A, III-D)","direct photometric alignment for tracking; point selection keeps DSO's gradient-based pixels but favours Shi-Tomasi corners, for which ORB descriptors are computed on keyframes only and stored in a DBoW3 bag-of-words database (Secs. III-B, III-C)","discrete keyframes","not_applicable","DBoW3 query among marginalised keyframes, ORB matching and RANSAC PnP initial guess, then Gauss-Newton Sim(3) estimate minimising 3D point alignment and 2D reprojection terms using depths from the sliding window (Sec. III-C)","Sim(3) pose-graph optimisation (g2o) over keyframes; no global bundle adjustment (Secs. III-D, V)","keyframe pose graph with sparse inverse-depth points from DSO; a point cloud map is shown before and after loop closure (Fig. 7)","photometric camera calibration where the dataset provides it (TUM-Mono)","loop-corrected keyframe trajectory up to monocular scale and a sparse point cloud from DSO's points (Figs. 1, 7)","laptop with Intel i7-4770HQ and 16 GB RAM (Ubuntu 18.04); LDSO point selection 0.0218 s per keyframe versus 0.0126 s for DSO; pose-graph optimisation runs in a separate thread (Sec. IV-D; Table II)","https:\u002F\u002Fgithub.com\u002Ftum-vision\u002FLDSO","GPL-3.0 (LICENSE.txt)",[49,53,56],{"relation":50,"title":51,"doi_or_url":52},"preprint","LDSO: Direct Sparse Odometry with Loop Closure (arXiv v1)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.01111",{"relation":54,"title":55,"doi_or_url":46},"code_release","tum-vision\u002FLDSO (project page vision.in.tum.de\u002Fresearch\u002Fvslam\u002Fldso)",{"relation":57,"title":58,"doi_or_url":59},"predecessor_method","Direct Sparse Odometry (DSO), the odometry front end that LDSO extends","10.1109\u002FTPAMI.2017.2658577",{"id":5,"kind":61,"shortName":7,"title":8,"authors":62,"year":9,"venue":67,"venueType":68,"publisher":69,"volumeIssuePages":70,"doi":71,"arxivId":72,"url":52,"firstPublicDate":73,"publicationStatus":16,"metadataStatus":74,"fulltextStatus":15,"era":10,"classicReason":39,"codeUrl":46,"cluster":11,"topics":75,"mdpi":76,"verification":77,"label":6,"fulltextRoute":78,"versionRead":79,"addedByCensus":80},"method",[63,64,65,66],"Xiang Gao","Rui Wang","Nikolaus Demmel","Daniel Cremers","2018 IEEE\u002FRSJ International Conference on Intelligent Robots and Systems (IROS)","conference","IEEE","pp. 2198-2204","10.1109\u002Firos.2018.8593376","1808.01111","2018-08-03","metadata_verified",[11],false,"corrected","arXiv","arXiv v1 (2018-08-03); IEEE version of record not read",true,[82,89,96],{"category":83,"model":84,"canonical":84,"role":85,"dataset":86,"specs":87,"locator":88},"compute","Intel i7-4770HQ laptop, 16GB RAM","compute for runtime",null,"Ubuntu 18.04","Sec. IV-D",{"category":90,"model":91,"canonical":91,"role":92,"dataset":93,"specs":94,"locator":95},"stereo_camera","EuRoC MAV stereo camera (model not reported; used monocularly)","dataset sensor","EuRoC MAV","stereo images with synchronised IMU and ground-truth trajectories; 11 sequences","Sec. IV-B",{"category":97,"model":98,"canonical":98,"role":92,"dataset":99,"specs":100,"locator":101},"camera","TUM-Mono camera (model not reported)","TUM-Mono","50 indoor and outdoor sequences with photometric calibration and start equal to end point","Sec. IV-A",[],1790510662367]