[{"data":1,"prerenderedAt":98},["ShallowReactive",2],{"method-basalt2020":3},{"method":4,"reference":55,"equipment":77,"figures":97,"results":82},{"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":30,"platform":33,"estimator":35,"association":36,"timeModel":37,"deskew":38,"loopClosure":39,"globalOptimization":40,"mapRepresentation":41,"prior":42,"outputGeometry":43,"compute":44,"codeUrl":45,"codeLicense":46,"relatedVersions":47},"basalt2020","Usenko et al., 2020","Basalt","Visual-Inertial Mapping With Non-Linear Factor Recovery",2020,"recent","C08","full_slam_with_global_correction","Basalt 採兩層架構整合視覺慣性里程計與全域一致建圖。下層為立體視覺 VIO，以 KLT 光流追蹤 FAST 角點，在滑動視窗中聯合最佳化重投影與 IMU 預積分誤差，並以首次估計 Jacobian 做部分邊際化。當關鍵影格被邊際化時，作者用非線性因子還原（NFR）把邊際化先驗近似成關鍵影格間的相對位姿因子與橫滾俯仰因子。上層以 ORB 特徵在關鍵影格間匹配並做光束法平差，結合這些因子得到重力對齊的全域地圖，不需估計每個關鍵影格的速度與偏差。","Basalt pairs a KLT-based stereo VIO fixed-lag smoother with keyframe bundle adjustment on ORB features, transferring VIO information to the global map through relative-pose and roll-pitch factors obtained by non-linear factor recovery, which yields gravity-aligned, globally consistent visual-inertial maps.","full_text_reviewed","peer_reviewed_published","supplementary","論文未在營建工地測試；只在 EuRoC 室內 MAV 資料評估。其重力對齊的全域一致關鍵影格地圖，以及相對低的運算量，對以立體相機與 IMU 做施工現場巡檢定位有參考價值；輸出為稀疏 ORB 地標，若要得到工程點雲需額外稠密重建（推論）。",[20,21],"public_benchmark","independent_reference",[23,24,25,26,27],"Proposed VIO best on eight of ten EuRoC sequences among VIO methods (Table I; Sec. VI-b)","Proposed VI mapping reaches 0.02 to 0.10 m RMS ATE on EuRoC and clearly beats VI ORB-SLAM on machine-hall sequences with long keyframe intervals (Table I)","Properly weighted recovered factors beat pure BA and identity-weighted factors in accuracy and robustness (Table I; Sec. VI-c)","Global optimisation state is about 2.5 times smaller because velocities and biases are not estimated (Sec. VI-d)","Fast: VIO 7.83 ms per frame and whole MH_05 about four times faster than real time (Sec. VI-d)",[29],"Camera intrinsics and camera-IMU extrinsics are assumed static and known from calibration (Sec. IV-B)",[31,32],"stereo camera","IMU",[34],"UAV (EuRoC MAV machine hall and Vicon room sequences)","two layers: (1) stereo VIO as fixed-lag smoother (Gauss-Newton over 7 pose-only keyframes and 3 latest states with velocity and biases) combining reprojection and preintegrated IMU terms, Schur-complement partial marginalisation with first-estimate Jacobians; (2) visual-inertial mapping as keyframe bundle adjustment of ORB landmarks plus relative-pose and roll-pitch factors recovered from the VIO marginalisation prior by non-linear factor recovery (KL-divergence minimisation) (Secs. IV, V)","VIO: FAST corners in a 50 pixel grid (80 to 120 features) tracked by pyramidal inverse-compositional KLT with SE(2) patch warp and locally scaled SSD, forward-backward consistency check; mapping: ORB features detected and matched between keyframes (Secs. IV-A, V-A, VI-a)","discrete frames with IMU preintegration between consecutive frames (Sec. IV-B3)","not_applicable","implicit, through ORB keypoint matching between keyframes in the global bundle adjustment (Sec. V)","keyframe bundle adjustment with recovered non-linear relative-pose and roll-pitch factors (yaw and absolute-position factors dropped); map is gravity aligned (Secs. V-A to V-C)","keyframe poses and ORB landmark positions (inverse distance with stereographic bearing parameterisation) in a gravity-aligned global map; VIO landmarks hosted in keyframes (Secs. IV-B, V-A)","camera projection functions (intrinsics) and camera-IMU extrinsics are assumed static and known from calibration (Sec. IV-B); the paper does not state how IMU noise parameters are obtained","VIO pose for every frame; globally consistent, gravity-aligned keyframe trajectory and sparse ORB landmark map (Fig. 1)","Intel E5-1620 (4 cores, 8 threads), highly parallel implementation; VIO 7.83 ms per frame on average (5.5 to 9.4 ms); mapping 52.8 ms per keyframe; MH_05 (114 s) processed in 19.2 s VIO plus 9.7 s mapping (Sec. VI-d; Table II)","https:\u002F\u002Fgitlab.com\u002FVladyslavUsenko\u002Fbasalt","BSD-3-Clause (GitLab project licence metadata)",[48,52],{"relation":49,"title":50,"doi_or_url":51},"preprint","Visual-Inertial Mapping with Non-Linear Factor Recovery (arXiv v1 to v3)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.06504",{"relation":53,"title":54,"doi_or_url":45},"code_release","Basalt (GitLab VladyslavUsenko\u002Fbasalt; project page vision.in.tum.de\u002Fresearch\u002Fvslam\u002Fbasalt)",{"id":5,"kind":56,"shortName":7,"title":8,"authors":57,"year":9,"venue":63,"venueType":64,"publisher":65,"volumeIssuePages":66,"doi":67,"arxivId":68,"url":51,"firstPublicDate":69,"publicationStatus":16,"metadataStatus":70,"fulltextStatus":15,"era":10,"classicReason":38,"codeUrl":45,"cluster":11,"topics":71,"mdpi":72,"verification":73,"label":6,"fulltextRoute":74,"versionRead":75,"addedByCensus":76},"method",[58,59,60,61,62],"Vladyslav Usenko","Nikolaus Demmel","David Schubert","Jörg Stückler","Daniel Cremers","IEEE Robotics and Automation Letters","journal","IEEE","5(2):422-429","10.1109\u002Flra.2019.2961227","1904.06504","2019-04-13","metadata_verified",[11],false,"corrected","arXiv","arXiv v3 (2020-05-30, posted after RA-L publication); IEEE version of record not read",true,[78,85,92],{"category":79,"model":80,"canonical":80,"role":81,"dataset":82,"specs":83,"locator":84},"compute","Intel E5-1620","compute for runtime",null,"4 cores, 8 virtual cores; implementation uses all available CPU resources","Sec. VI-d",{"category":86,"model":87,"canonical":87,"role":88,"dataset":89,"specs":90,"locator":91},"stereo_camera","EuRoC MAV stereo camera (model not reported in this paper)","dataset sensor","EuRoC MAV","MH_05 has 2273 stereo frames over 114 s; V2_03 has more than 400 missing frames for one camera","Sec. VI-d; Table I note",{"category":93,"model":94,"canonical":94,"role":88,"dataset":89,"specs":95,"locator":96},"imu","EuRoC MAV IMU (model not reported in this paper)","not_reported (IMU measurements preintegrated between consecutive frames)","Secs. IV-B3, VI",[],1790510662224]