traffic op• Data kinds: signal → table
• Call: import fullseye as fs; fs.ledger.ou_estimate(x, dt: 'float') -> 'Dict[str, float]' (to call the implementation directly, import drivetraffic; drivetraffic.ou_estimate(x, dt: 'float') -> 'Dict[str, float]'; from the registry, opsdrive.get("ou_estimate"))
Reads the parameters of lateral wander (an OU process with mean 0 dX = −θX dt + σ dW) from a sequence of observations at uniform spacing dt.
Conditional maximum likelihood for the exact discretisation x_{k+1} = φ x_k + ε_k (φ = e^{−θ dt}, ε ~ N(0, q²), q² = σ²(1 − φ²)/(2θ)):
φ̂ = Σ x_k x_{k+1} / Σ x_k², q̂² = mean((x_{k+1} − φ̂ x_k)²), θ̂ = −ln φ̂ / dt, σ̂ = q̂ sqrt(2θ̂ / (1 − φ̂²))
(Because ln is used rather than Euler's (1 − φ̂)/dt, there is no bias even when dt is coarse.) Standard errors use the asymptotic formulas: se(φ̂) = sqrt((1 − φ²)/n), se(q̂) = q/sqrt(2n), and the delta method for θ̂ and σ̂. sigma_increment = sqrt(mean(Δx²)/dt) is a rough estimate that does not use θ (E[Δx²] = σ²(1 − φ)/θ, so it tends to σ as θ dt → 0. When a series with a long correlation time is observed over a short span, it reads σ more stably than the sample SD of the positions).
Returns dict: theta, sigma, sd (stationary SD σ/√(2θ)), phi, q, n (number of increments), se_theta, se_sigma, sigma_increment.
Raises ValueError: not 1-D, fewer than 3 points, or non-finite; dt ≤ 0; φ̂ ∉ (0, 1) (at this dt it does not look like a mean-reverting process).
• 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_driving_traffic — py -3.11 examples/poc_driving_traffic.py
table as input)course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same
traffic)idm_accel · idm_equilibrium_gap · idm_platoon_simulate · driver_style · lateral_wobble · social_force_step · pedestrian_crossing · occlusion_reveal_distance
*Provenance: drivetraffic.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.