[{"data":1,"prerenderedAt":99},["ShallowReactive",2],{"method-dvoslam2013":3},{"method":4,"reference":58,"equipment":80,"figures":98,"results":69},{"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":33,"platform":35,"estimator":38,"association":39,"timeModel":40,"deskew":41,"loopClosure":42,"globalOptimization":43,"mapRepresentation":44,"prior":45,"outputGeometry":46,"compute":47,"codeUrl":48,"codeLicense":49,"relatedVersions":50},"dvoslam2013","Kerl et al., 2013","DVO-SLAM","Dense visual SLAM for RGB-D cameras",2013,"classic","C08","full_slam_with_global_correction","DVO-SLAM 以稠密方式對齊 RGB-D 影像，同時最小化所有像素的光度誤差與深度誤差，並以雙變量 t 分布自動調整兩項誤差的權重，降低離群值影響。系統採影格對關鍵影格追蹤，以位姿估計共變異數的熵比值決定何時建立新關鍵影格，並用同一熵比值驗證以距離搜尋得到的迴圈閉合候選。所有成功的匹配組成位姿圖，以 g2o 最佳化以修正累積漂移。","DVO-SLAM aligns RGB-D frames densely by minimising t-distribution-weighted photometric and depth errors, selects keyframes and validates metric loop-closure candidates with an entropy-ratio test on the motion covariance, and optimises the keyframe pose graph with g2o.","full_text_reviewed","peer_reviewed_published","supplementary","論文未在營建工地測試；全部評估使用 TUM RGB-D 公開資料集（真值由外部動作捕捉系統提供；論文未描述各序列的場景與相機攜帶方式）。作者指出迴圈搜尋以距離為準，適用於空間受限的室內環境，並在低紋理或低結構場景表現較佳，這對室內裝修階段以 RGB-D 相機掃描白牆或空房有參考價值，但系統未輸出量化的點雲精度（推論）。",[20,21],"public_benchmark","independent_reference",[23,24,25,26,27],"Combined RGB and depth odometry is best on scenes with only structure or only texture and generalises better across scene types (Table I)","Keyframes reduce drift by 16% on average and pose-graph optimisation raises the improvement to 20% (Table II)","Average ATE RMSE on the fr1 sequences (excluding fr1\u002Ffloor) drops from 0.19 m (frame-to-frame) to 0.07 m (keyframes plus optimisation) (Sec. V)","Best ATE on five of eight datasets where all systems report results, with average ATE 0.034 m versus 0.054 m (RGB-D SLAM), 0.043 m (MRSMap) and 0.297 m (KinFu) (Table III)","The depth term stabilises estimates during sudden intensity changes from auto-exposure (Sec. V)",[29,30,31,32],"Incorrect loop closures caused high drift on fr1\u002Ffloor and fr1\u002Fplant (v) (Sec. V; Table II)","Combined odometry is slightly worse than RGB-only on scenes with both structure and texture (Table I)","Loop-closure search is metric and designed for space-restricted indoor scenes with accurate odometry (Sec. IV-B)","Dense 3D model generation from the optimised trajectory was left for future work (Sec. VI)",[34],"RGB-D camera",[36,37],"TUM RGB-D benchmark sequences (fr1, fr2\u002Fdesk, fr3\u002Foffice and the structure and texture sequences)","the paper does not state how the camera was carried","dense frame-to-keyframe alignment minimising a bivariate t-distributed photometric and depth error by iteratively reweighted Gauss-Newton on se(3), coarse-to-fine over three resolutions up to 320 x 240; covariance from the inverse approximate Hessian; keyframe pose graph optimised with g2o (Secs. III, IV-C)","direct: all pixels warped with the depth map (photometric residual plus depth residual equivalent to point-to-plane ICP with projective lookup); no feature matching (Sec. III-D)","discrete RGB-D frames","not_applicable","metric nearest-neighbour search for keyframes within a sphere around the current keyframe, validated by the entropy ratio at coarse and then higher resolution; extra loop search for every keyframe at the end of a sequence (Sec. IV-B, IV-C)","g2o pose-graph optimisation over keyframe poses with edges weighted by the covariance of the relative motion estimates (Sec. IV-C)","pose graph of keyframes (RGB-D images); a point cloud can be formed from the optimised trajectory (Fig. 1 text; Sec. IV-C)","none","optimised keyframe trajectory; the corrected trajectory allows a consistent point cloud model of the scene, while high-quality 3D model generation is left as future work (Secs. I, IV-C, VI)","Intel Core i7-2600 at 3.40 GHz with 16 GB RAM; frame-to-keyframe tracking about 32 ms; loop detection and optimisation (map update) averaging 135 ms in a separate thread (Sec. V)","https:\u002F\u002Fgithub.com\u002Ftum-vision\u002Fdvo_slam","GPL-3.0 for dvo_core, dvo_ros, dvo_slam and dvo_benchmark; bundled sophus under MIT (README licence section; no LICENSE file in the repository root)",[51,55],{"relation":52,"title":53,"doi_or_url":54},"predecessor_method","Robust odometry estimation for RGB-D cameras (Kerl, Sturm, Cremers, ICRA 2013), the dense visual odometry that this paper extends (cited as [7])","10.1109\u002FICRA.2013.6631104",{"relation":56,"title":57,"doi_or_url":48},"code_release","tum-vision\u002Fdvo_slam (dvo_core, dvo_ros, dvo_slam, dvo_benchmark)",{"id":5,"kind":59,"shortName":7,"title":8,"authors":60,"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",[61,62,63],"Christian Kerl","Jürgen Sturm","Daniel Cremers","2013 IEEE\u002FRSJ International Conference on Intelligent Robots and Systems (IROS)","conference","IEEE","pp. 2100-2106","10.1109\u002Firos.2013.6696650",null,"https:\u002F\u002Fvision.in.tum.de\u002F_media\u002Fspezial\u002Fbib\u002Fkerl13iros.pdf","2013-11","metadata_verified","reproducible baseline and principle reused: dense photometric plus depth RGB-D odometry with t-distribution weighting and entropy-ratio keyframe and loop-closure tests in a keyframe pose graph; the dense RGB-D odometry of its ICRA 2013 predecessor (DVO), not DVO-SLAM itself, is one of the odometers evaluated in the ICL-NUIM benchmark (handa2014iclnuim).",[11],false,"corrected","author copy","author PDF from the TUM Computer Vision Group site (created 2013-07-30, IROS 2013 camera-ready layout); IEEE version of record not read",true,[81,88,93],{"category":82,"model":83,"canonical":83,"role":84,"dataset":85,"specs":86,"locator":87},"rgbd","RGB-D camera of the TUM RGB-D benchmark (model not named in this paper)","dataset sensor","TUM RGB-D","not_reported (the method processes the images coarse-to-fine at three resolutions up to 320 x 240 pixels)","Sec. V",{"category":89,"model":90,"canonical":90,"role":91,"dataset":85,"specs":92,"locator":87},"other","external motion capture system (model not reported)","reference or ground truth","accurate ground-truth trajectory",{"category":94,"model":95,"canonical":95,"role":96,"dataset":69,"specs":97,"locator":87},"compute","Intel Core i7-2600","compute for runtime","3.40GHz, 16GB RAM; visual odometry and SLAM run in separate threads",[],1790510664895]