LSD-SLAM tracks a monocular camera by direct photometric alignment and builds a Sim(3) pose graph of keyframes carrying filtered semi-dense depth maps, explicitly modelling scale drift.

技術屬性

欄位內容為文獻擷取紀錄的原文用語(英文),以原文為據;「未查證」表示本研究尚未讀到該資訊,不代表該方法不具備此能力。

LSD-SLAM 的技術屬性
感測輸入monocular camera
原文測試平台handheld
狀態估計weighted Gauss-Newton direct image alignment on se(3)/sim(3); keyframe pose-graph optimisation with Sim(3) edges (Sec. 2.2, 3.1)
資料關聯direct photometric alignment on high-gradient (semi-dense) pixels; depth by filtering many small-baseline stereo comparisons (abstract; Sec. 3.1)
時間表示discrete poses (keyframes)
去畸變不適用
迴圈閉合candidates from the ten closest keyframes plus an appearance-based candidate (OpenFABMAP, ref. [11]), accepted after a reciprocal sim(3) tracking consistency check (Sec. 3.5 Constraint Acquisition)
全域最佳化Sim(3) pose-graph optimisation of keyframes, run continuously in the background (Sec. 3.6 Map optimization; Fig. 3; conclusion)
地圖表示Pose graph of keyframes; each keyframe stores the image, a semi-dense inverse depth map and its variance defined only near sufficiently large intensity gradients, scaled to mean inverse depth one; edges hold sim(3) transforms with covariance; the map can be exported as point clouds
先驗資訊No prior map. The method bootstraps from a first keyframe with random depth and large variance and needs sufficient translational motion in the first seconds; for the TUM RGB-D evaluation the very first sensor depth map was used to bootstrap and obtain the correct initial scale
可輸出幾何semi-dense point cloud from keyframe depth maps and poses (conclusion); monocular, scale not metric
計算需求Real time on a CPU; the pipeline figure assumes 640x480 images at 30 Hz and map optimisation runs continuously in the background; no CPU model or timing numbers are reported (an odometry-only variant is cited as running on a smartphone, ref. [22])

使用設備

原文使用的感測器、運算硬體與載具(equipment)。型號保留原文寫法,連結到設備頁中同一型號的歸併名稱;角色依原文用途分為方法輸入、資料集感測器、執行運算平台、參考或真值量測(reference or ground truth)與比較對象設備。

原文使用的設備
類別型號(原文寫法)角色資料集原文規格出處
相機hand-held monocular camera (model not stated)方法輸入未標示pipeline figure assumes 640x480 at 30 Hz; used for the qualitative outdoor trajectories of about 500 m(Engel et al., 2014, Sec. 4, 4.1; Fig. 3)
RGB-D 相機TUM RGB-D benchmark sensor (model not stated)資料集感測器TUM RGB-Dimages used as monocular input; the first depth map used only for bootstrapping and initial scale(Engel et al., 2014, Sec. 4.2)

作者報告的優勢與限制

優勢

限制

營建工程相關證據

論文未報告營建測試;以手持序列及 TUM RGB-D 評估。半稠密點雲僅來自影像梯度區域且尺度未定,用於工程幾何時需外部尺度與參考控制(推論)。

原文驗證環境:公開基準、受控實驗、模擬

報告的性能數據

以下是原文作者報告的性能數值(author-reported results),不是本研究重新量測的結果。每張圖只並列同一個比較組(comparison group,同一張表、同一組實驗設定)內的方法;不同比較組之間的數值不可直接比較,也不構成排名。

本方法共出現在 8 個比較組,合計 87 筆紀錄。以下列出本方法紀錄最多的 4 組,其餘 4 組列在最後,並連到性能比較頁。

Tateno et al., 2017 · Table 1 本方法 40 筆

表格設定(擷取紀錄原文):Percentage of key-frame depth values within 10% of ground-truth depth (accuracy and density together) (Tateno et al., 2017, Table 1)

Perc. Correct Depth (error < 10%),ICL-NUIM · office0

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Tateno et al., 2017 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:不適用;對齊方式:不適用;單位:%;場景:synthetic indoor (ICL-NUIM)

資料來源作者報告值(Tateno et al., 2017, Table 1)

數值與出處
方法(原文寫法)報告值出處
CNN-SLAM (Our Method)原文提出19.41%(Tateno et al., 2017, Table 1)
LSD-BS [4] (LSD-SLAM bootstrapped with ground-truth depth)本方法0.603%(Tateno et al., 2017, Table 1)
LSD [4] (LSD-SLAM)本方法0.335%(Tateno et al., 2017, Table 1)
ORB [20] (ORB-SLAM)0.018%(Tateno et al., 2017, Table 1)
Laina [16] (CNN depth fed to point-based fusion)17.194%(Tateno et al., 2017, Table 1)
Remode [23] (REMODE, poses from LSD-BS)4.479%(Tateno et al., 2017, Table 1)

Mur-Artal et al., 2015 · Table III 本方法 16 筆

指標Absolute KeyFrame Trajectory RMSE

表格設定(擷取紀錄原文):TUM RGB-D keyframe ATE RMSE (cm), median over 5 executions; ORB-SLAM, PTAM (two manually chosen initial frames) and LSD-SLAM (first 10 keyframes discarded) aligned with Sim(3); RGBD-SLAM trajectories from the benchmark website aligned with SE(3), Sim(3) value in brackets; X = tracking lost (Mur-Artal et al., 2015, Table III)

Absolute KeyFrame Trajectory RMSE,TUM RGB-D · fr1_xyz

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Mur-Artal et al., 2015 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:均方根誤差(RMSE);對齊方式:Sim(3) 相似對齊;單位:cm;場景:indoor, hand-held

資料來源作者報告值(Mur-Artal et al., 2015, Table III)

數值與出處
方法(原文寫法)報告值出處
ORB-SLAM原文提出0.9 cm(Mur-Artal et al., 2015, Table III)
PTAM1.15 cm(Mur-Artal et al., 2015, Table III)
LSD-SLAM本方法9 cm(Mur-Artal et al., 2015, Table III)

Forster et al., 2017b · Table I 本方法 11 筆

指標absolute translation error (RMSE)

表格設定(擷取紀錄原文):EuRoC; absolute translation error RMSE of keyframe positions after least-squares translation and scale alignment, averaged over five runs; loop closure deactivated for ORB-SLAM and LSD-SLAM; ORB-SLAM and DSO values taken from the DSO paper [42] with and without enforced real-time execution; x = tracking failed (version of record Table I) (Forster et al., 2017b, Table I)

absolute translation error (RMSE),EuRoC · Machine Hall 01

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Forster et al., 2017b 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:均方根誤差(RMSE);對齊方式:Sim(3) 相似對齊;單位:m;場景:indoor machine hall, micro aerial vehicle

資料來源作者報告值(Forster et al., 2017b, Table I)

數值與出處
方法(原文寫法)報告值出處
SVO (stereo)原文提出0.08 m(Forster et al., 2017b, Table I)
SVO (stereo, edgelets)原文提出0.08 m(Forster et al., 2017b, Table I)
SVO (stereo, edgelets + prior)原文提出0.04 m(Forster et al., 2017b, Table I)
SVO (stereo, bundle adjustment)原文提出0.04 m(Forster et al., 2017b, Table I)
SVO (monocular)原文提出0.17 m(Forster et al., 2017b, Table I)
SVO (monocular, edgelets)原文提出0.17 m(Forster et al., 2017b, Table I)
SVO (monocular, edgelets + prior)原文提出0.1 m(Forster et al., 2017b, Table I)
SVO (monocular, bundle adjustment)原文提出0.06 m(Forster et al., 2017b, Table I)
ORB-SLAM (monocular, no loop-closure)0.02 m(Forster et al., 2017b, Table I)
ORB-SLAM (monocular, no loop, real-time)0.61 m(Forster et al., 2017b, Table I)
DSO (monocular)0.05 m(Forster et al., 2017b, Table I)
DSO (monocular, real-time)0.05 m(Forster et al., 2017b, Table I)
LSD-SLAM (monocular, no loop-closure)本方法0.18 m(Forster et al., 2017b, Table I)

Czarnowski et al., 2020 · Table II 本方法 8 筆

指標Perc. Correct Depth [%]

表格設定(擷取紀錄原文):Percentage of key-frame pixels with depth within 10% of ground truth; DeepFactors trajectory and depth scaled by the optimal scale from the TUM scripts; other values taken from the CNN-SLAM paper (Czarnowski et al., 2020, Table II)

Perc. Correct Depth [%],ICL-NUIM · office0

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Czarnowski et al., 2020 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:不適用;對齊方式:原文未報告;單位:%;場景:indoor (synthetic ICL-NUIM, real TUM)

資料來源作者報告值(Czarnowski et al., 2020, Table II)

數值與出處
方法(原文寫法)報告值出處
CNN-SLAM [ 18 ]19.41%(Czarnowski et al., 2020, Table II)
LSD-BS [ 19 ]本方法0.6%(Czarnowski et al., 2020, Table II)
Laina [ 37 ]17.19%(Czarnowski et al., 2020, Table II)

其他比較組

列出其餘 4 個比較組

來源

  • Engel et al., 2014

    Jakob Engel, Thomas Schöps, Daniel Cremers(2014)LSD-SLAM: Large-Scale Direct Monocular SLAMComputer Vision – ECCV 2014 (Lecture Notes in Computer Science), pp. 834-849

    同儕審查已出版已讀全文經典查證後修正

回到方法圖鑑

選擇開啟Esc關閉