[{"data":1,"prerenderedAt":112},["ShallowReactive",2],{"method-rovio2015":3},{"method":4,"reference":59,"equipment":82,"figures":111,"results":71},{"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":37,"estimator":40,"association":41,"timeModel":42,"deskew":43,"loopClosure":44,"globalOptimization":44,"mapRepresentation":45,"prior":46,"outputGeometry":47,"compute":48,"codeUrl":49,"codeLicense":50,"relatedVersions":51},"rovio2015","Bloesch et al., 2015","ROVIO","Robust visual inertial odometry using a direct EKF-based approach",2015,"classic","C08","odometry_with_local_mapping","ROVIO 是單目視覺慣性里程計，把影像塊的像素強度誤差直接當作 EKF 更新的創新項，而非使用特徵點重投影誤差。整個濾波狀態採機器人中心（robocentric）表示，地標以方位向量加上反距離參數化，並以最小維度的流形差分表示不確定度，因此特徵在第二次觀測時即可使用，系統不需額外初始化程序。多層影像塊在影像金字塔上追蹤，強度誤差經 QR 分解降維以維持即時運算，同時線上估計 IMU 偏差與相機外參。","ROVIO is a monocular VIO that feeds photometric errors of multilevel image patches directly into a robocentric EKF, with landmarks parameterised by bearing vector and inverse distance, enabling undelayed feature use, power-up-and-go operation and online extrinsic calibration in real time on one CPU core.","full_text_reviewed","peer_reviewed_published","background","論文未報告營建工地測試；手持實驗與 UAV 飛行都在動作捕捉系統範圍內進行並以其為參考。直接法影像塊與強度誤差回饋在低紋理或快速運動下的穩健性，對施工現場手持或無人機巡檢的位姿估計有參考價值，但系統只輸出稀疏地標，無法直接產生工程點雲（推論）。",[20,21],"controlled_experiment","independent_reference",[23,24,25,26,27],"No initialisation procedure needed because of the robocentric inverse-distance landmark parametrisation (abstract; Sec. II-A)","Tracks hand-held motion with mean rotation rate about 3.5 rad\u002Fs and peaks up to 8 rad\u002Fs against motion capture (Sec. IV-C)","Relative position error in a 1 min slow-motion run tends to be similar to, and often slightly better than, a batch optimisation framework along the lines of OKVIS (Sec. IV-B, Fig. 3; values only plotted)","Accuracy nearly independent of the number of tracked features above 20 (Sec. IV-B)","Output used directly in the control loop of a multirotor UAV from take-off to landing with calibration converging during take-off (Sec. IV-D)",[29,30,31,32,33],"A divergence mode exists when the velocity estimate diverges (missing motion or many outliers): feature distances are pushed to infinity, which removes the corrective effect (Sec. IV-C)","Yaw is unobservable and drifts slowly (Sec. IV-C)","The IMU-camera translation needs much rotational motion to converge and the accelerometer bias converges slowly (Sec. IV-C)","A position offset against motion capture was observed on the UAV and attributed mainly to online calibration (Sec. IV-D)","Evaluation limited to short motion-capture sequences; quantitative comparison only in plots (Sec. IV; inference)",[35,36],"monocular camera","IMU",[38,39],"handheld (VI-Sensor; slow and fast motion with motion-capture ground truth)","UAV (multirotor with forward-looking visual-inertial sensor; filter output used for flight control)","EKF with a fully robocentric state (position, velocity, attitude, IMU biases, camera-IMU extrinsics, and per feature a bearing vector plus inverse-distance parameter) using minimal boxplus differences on SO(3) and S2; linearisation point of uncertain features improved by a patch search; an iterated EKF is named as an alternative (Secs. II-A, II-C)","direct: multilevel 8 x 8 pixel patches on a 4-level image pyramid tracked inside the filter; mean-subtracted intensity errors reduced by QR decomposition to a 2D innovation per feature; affine patch warping from two extra bearing vectors; FAST candidates ranked by a multi-level Shi-Tomasi score with bucketing; Mahalanobis outlier rejection (Secs. II-C, III)","discrete; continuous IMU-driven dynamics discretised with Euler forward integration; one update per image (IMU 200 Hz, images 20 Hz in the experiments) (Secs. II-B, IV-A)","not_applicable","none","up to 50 robocentric landmarks (bearing vector plus inverse distance) with multilevel patches held in the filter state (Sec. IV-A)","none; camera intrinsics assumed known (factory calibration); IMU-camera extrinsics roughly guessed with translation set to zero and estimated online (Sec. IV-A)","IMU pose, robocentric velocity, IMU biases and camera-IMU extrinsics with covariance; sparse landmark estimates; no dense map","single core of an Intel i7-2760QM: 6.65 ms per image with 10 features up to 29.72 ms with 50 features (Table I); run on board a UAV with 50 features at 20 Hz (Sec. V)","https:\u002F\u002Fgithub.com\u002Fethz-asl\u002Frovio","BSD-style (LICENSE file: Copyright (c) 2014, Autonomous Systems Lab, redistribution permitted with conditions)",[52,56],{"relation":53,"title":54,"doi_or_url":55},"journal_extension","Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedback (IJRR 36(10):1053-1072, 2017; Bloesch, Burri, Omari, Hutter, Siegwart); metadata checked in Crossref, content not read","10.1177\u002F0278364917728574",{"relation":57,"title":58,"doi_or_url":49},"code_release","ethz-asl\u002Frovio (open-source C++ implementation referenced as [2] in the paper)",{"id":5,"kind":60,"shortName":7,"title":8,"authors":61,"year":9,"venue":66,"venueType":67,"publisher":68,"volumeIssuePages":69,"doi":70,"arxivId":71,"url":72,"firstPublicDate":73,"publicationStatus":16,"metadataStatus":74,"fulltextStatus":15,"era":10,"classicReason":75,"codeUrl":49,"cluster":11,"topics":76,"mdpi":77,"verification":78,"label":6,"fulltextRoute":79,"versionRead":80,"addedByCensus":81},"method",[62,63,64,65],"Michael Bloesch","Sammy Omari","Marco Hutter","Roland Siegwart","2015 IEEE\u002FRSJ International Conference on Intelligent Robots and Systems (IROS)","conference","IEEE","pp. 298-304","10.1109\u002Firos.2015.7353389",null,"https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F7353389","2015-09","metadata_verified","reproducible baseline and principle reused: first public 2015-09, before the recent window; a widely used open-source direct (photometric patch) filter VIO and a common baseline in later VIO papers such as S-MSCKF.",[11],false,"corrected","NTU institutional (Chrome)","version of record (IEEE Xplore HTML full text, IROS 2015)",true,[83,89,94,100,105],{"category":84,"model":85,"canonical":85,"role":86,"dataset":71,"specs":87,"locator":88},"stereo_camera","VI-Sensor (two global-shutter wide-VGA 1\u002F3 inch imagers)","method input","fronto-parallel stereo, lenses with 120 deg diagonal field of view, factory calibrated pinhole plus radial-tangential model, hardware time-synchronised to the IMU with mid-exposure triggering, 20 Hz; only one camera used","Sec. IV-A",{"category":90,"model":91,"canonical":92,"role":86,"dataset":71,"specs":93,"locator":88},"imu","ADIS 16448","ADIS16448","industrial grade, angular random walk 0.66 deg\u002Fsqrt(Hz), velocity random walk 0.11 m\u002Fs\u002Fsqrt(Hz), 200 Hz",{"category":95,"model":96,"canonical":96,"role":97,"dataset":71,"specs":98,"locator":99},"other","external motion capture system (model not reported)","reference or ground truth","pose ground truth; some bad tracking filtered out in the fast-motion run","Secs. IV-A, IV-C",{"category":101,"model":102,"canonical":102,"role":86,"dataset":71,"specs":103,"locator":104},"platform","multirotor UAV (model not reported)","forward-oriented visual-inertial sensor; filter output used for feedback control","Sec. IV-D",{"category":106,"model":107,"canonical":107,"role":108,"dataset":71,"specs":109,"locator":110},"compute","Intel i7-2760QM","compute for runtime","single core","Sec. IV-B; Table I",[],1790510660328]