[{"data":1,"prerenderedAt":113},["ShallowReactive",2],{"method-openvslam2019":3},{"method":4,"reference":62,"equipment":82,"figures":112,"results":87},{"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":36,"estimator":39,"association":40,"timeModel":41,"deskew":42,"loopClosure":43,"globalOptimization":44,"mapRepresentation":45,"prior":46,"outputGeometry":47,"compute":48,"codeUrl":49,"codeLicense":50,"relatedVersions":51},"openvslam2019","Sumikura et al., 2019","OpenVSLAM (stella_vslam)","OpenVSLAM: A Versatile Visual SLAM Framework",2019,"recent","C08","full_slam_with_global_correction","OpenVSLAM 是設計成可被第三方程式呼叫的視覺 SLAM 程式庫，演算法沿用 ORB-SLAM 類的間接法：追蹤模組以 ORB 特徵匹配估計每張影格位姿，建圖模組三角化新點並做局部光束法平差，全域模組負責迴圈偵測、位姿圖最佳化與全域光束法平差。其特點是同一架構支援單目、立體與 RGB-D 輸入，以及透視、魚眼與等距柱狀（360 度）相機模型，並可把地圖以 MessagePack 格式儲存與載入，在既有地圖上定位。","OpenVSLAM is a library-style indirect (ORB-based) graph SLAM framework with tracking, local mapping and global optimisation modules that supports monocular, stereo and RGB-D input, perspective, fisheye and equirectangular camera models, and map storage, loading and localisation on prebuilt maps.","full_text_reviewed","peer_reviewed_published","supplementary","論文未在營建工地測試；定量評估為 EuRoC 與 KITTI，另有 Panasonic LUMIX DMC-GX8 魚眼相機與 RICOH THETA V 等距柱狀相機的室內外定性建圖（戶外等距柱狀地圖為手持拍攝）。支援 360 度相機、地圖儲存與在既有地圖上定位，使其可能適用於以消費型全景相機記錄工地進度並重複定位，但這是推論，作者未做工地驗證，輸出也只是稀疏點雲。",[20,21],"public_benchmark","independent_reference",[23,24,25,26,27],"Tracking accuracy comparable to ORB-SLAM2 on EuRoC (monocular) and KITTI (stereo), and more accurate on the dark MH_04 and MH_05 sequences (Secs. 4.1, 4.2; Figs. 3, 5, plotted)","Lower tracking time than ORB-SLAM2: 23.84 versus 27.96 ms per frame mean on MH_02 and 56.32 versus 68.78 ms on KITTI 05 (Figs. 4, 6)","First open-source visual SLAM framework accepting equirectangular images, according to the authors (Sec. 3.2)","Equirectangular outdoor sequence of 15000 frames with working loop closing and global optimisation, and indoor tracking in texture-less areas (Sec. 5.2)","Maps can be stored, loaded and reused for localisation (Sec. 3.3)",[29,30,31,32],"Indirect method chosen because direct methods suffer with rolling-shutter consumer sensors, so weakly textured scenes rely on feature availability or wide field of view (Sec. 2.2) (inference)","Accuracy results are only plotted; no numeric ATE table (Secs. 4.1, 4.2)","Fisheye and equirectangular results are qualitative only (Sec. 5)","The original code release was later withdrawn; the maintained fork removed ORB_SLAM2 similarities from version 0.3 (stella_vslam README; not stated in the paper)",[34,35],"monocular, stereo or RGB-D camera","camera models: perspective, fisheye, equirectangular (360-degree)",[37,38],"hand-held equirectangular camera for the outdoor map (Fig. 1)","indoor equirectangular and indoor and outdoor fisheye videos (carrying mode not stated)","graph-based indirect SLAM following ORB-SLAM and ProSLAM: tracking by keypoint matching and pose optimisation; mapping module with triangulation and local bundle adjustment; global optimisation module with loop detection, pose-graph optimisation (g2o) and global bundle adjustment (Secs. 3, 3.1; Fig. 2)","ORB features matched to the local map, with an additional robust-matching frame-tracking method (Secs. 3.1, 4.1)","discrete frames","not_applicable","loop detection in the global optimisation module followed by pose-graph optimisation that also removes scale drift for monocular input; detection method not detailed in the paper (Sec. 3.1)","pose-graph optimisation and global bundle adjustment implemented with g2o (Sec. 3.1; Fig. 2)","keyframes and sparse 3D landmarks; map database stored and loaded in MessagePack format for reuse and localisation on prebuilt maps (Sec. 3.3)","optional prebuilt map for localisation-only mode (Sec. 3.3)","camera trajectory and a sparse 3D point map (Figs. 1, 7-9), exportable as a MessagePack map database","laptop Core i7-7820HK (2.90 GHz, 4 cores 8 threads), 32 GB RAM: mean tracking 23.84 ms per frame on EuRoC MH_02 (monocular) and 56.32 ms on KITTI 05 (stereo), lower than ORB-SLAM2 (Figs. 4, 6)","https:\u002F\u002Fgithub.com\u002Fstella-cv\u002Fstella_vslam","original xdspacelab release withdrawn (termination statement); fork stella_vslam under BSD-2-Clause (LICENSE.original AIST 2019 and LICENSE.fork stella-cv 2022); its README says versions earlier than 0.3 should be used as ORB_SLAM2 derivatives under GPL",[52,56,60],{"relation":53,"title":54,"doi_or_url":55},"preprint","OpenVSLAM: A Versatile Visual SLAM Framework (arXiv v1 to v3)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.01122",{"relation":57,"title":58,"doi_or_url":59},"code_release","xdspacelab\u002Fopenvslam (original release terminated; README now only links the termination statement)","https:\u002F\u002Fgithub.com\u002Fxdspacelab\u002Fopenvslam",{"relation":57,"title":61,"doi_or_url":49},"stella-cv\u002Fstella_vslam (community fork created 2021-01-31 to continue OpenVSLAM; README lists monocular, stereo and RGB-D, perspective, fisheye and equirectangular models, map store and load, localisation on prebuilt maps)",{"id":5,"kind":63,"shortName":7,"title":8,"authors":64,"year":9,"venue":68,"venueType":69,"publisher":70,"volumeIssuePages":71,"doi":72,"arxivId":73,"url":55,"firstPublicDate":74,"publicationStatus":16,"metadataStatus":75,"fulltextStatus":15,"era":10,"classicReason":42,"codeUrl":49,"cluster":11,"topics":76,"mdpi":77,"verification":78,"label":6,"fulltextRoute":79,"versionRead":80,"addedByCensus":81},"method",[65,66,67],"Shinya Sumikura","Mikiya Shibuya","Ken Sakurada","Proceedings of the 27th ACM International Conference on Multimedia (MM '19)","conference","ACM","pp. 2292-2295","10.1145\u002F3343031.3350539","1910.01122","2019-10-02","metadata_verified",[11],false,"corrected","arXiv","arXiv v3 (2023-04-06; same ACM MM '19 content, 6 pages); ACM version of record not read",true,[83,90,94,100,106],{"category":84,"model":85,"canonical":85,"role":86,"dataset":87,"specs":88,"locator":89},"camera","LUMIX DMC-GX8 with 8mm fisheye lens","method input",null,"30.0 fps; fisheye videos of about 6400 (outdoor) and 6700 (indoor) frames","Sec. 5.1",{"category":84,"model":91,"canonical":91,"role":86,"dataset":87,"specs":92,"locator":93},"THETA V","consumer equirectangular (360-degree) camera; 10.0 fps; 15000 frames outdoor, 1430 frames indoor","Sec. 5.2",{"category":95,"model":96,"canonical":96,"role":97,"dataset":87,"specs":98,"locator":99},"compute","Core i7-7820HK","compute for runtime","2.90GHz, 4C8T; 32GB RAM; laptop used for all evaluations","Sec. 4",{"category":84,"model":101,"canonical":101,"role":102,"dataset":103,"specs":104,"locator":105},"EuRoC MAV camera (model not reported; monocular use)","dataset sensor","EuRoC MAV","11 sequences with ground truth","Sec. 4.1",{"category":107,"model":108,"canonical":108,"role":102,"dataset":109,"specs":110,"locator":111},"stereo_camera","KITTI Odometry stereo camera (model not reported)","KITTI Odometry","11 sequences with ground truth; larger images than EuRoC","Sec. 4.2",[],1790510659299]