roverslip op• Data kinds: any → table
• Call: import fullseye as fs; fs.ledger.ground_shift_track(frames, pixel_size: 'float' = 1.0) -> 'dict' (to call the implementation directly, import roverslip; roverslip.ground_shift_track(frames, pixel_size: 'float' = 1.0) -> 'dict'; from the registry, opsdrive.get("ground_shift_track"))
> This operator's description has not been translated yet. The original text follows as it is.
地面を見下ろすカメラのコマ列から、隣り合うコマの並進を、窓つきの相互相関(整数)と
並進の Lucas–Kanade(副画素)で測り、累積する。
`frames は (T, H, W) の配列か同じ形の 2-D 配列の列(T ≥ 2)。pixel_size` は地面での画素の大きさ [m]。
返り値 `{"step": (T−1, 2) の (drow, dcol) [m]、"position": (T, 2) の累積 [m]、"peak": (T−1,) 合わせた後の正規化相関}`。
`step` は 像の中で模様が動いた量(カメラ・車体の移動はその逆向き —— 前に進むと地面は後ろへ流れる)。
1 コマの移動は像の 1/4 程度まで(相関は周期的なので、半分を越えると折り返す)。
• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).
• Operator provenance and references — the sources of the research/methods this op family came from.
• The canonical algorithm (author, year) and its uses are named in the family usage guide above.
• poc_rover_slip_risk_path — py -3.11 examples/poc_rover_slip_risk_path.py
table as input)course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same
roverslip)bekker_pressure · bekker_wheel_sinkage · wheel_forces · wheel_sinkage · wheel_traction_curve · slope_slip_curve · odometry_slip · slip_gp_fit
*Provenance: roverslip.py — DRIVE operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.