humanoid op• Data kinds: table × matrix × matrix → table
• Call: import fullseye as fs; fs.ledger.world_camera_impostors(world: 'dict', pose, K, width: 'int' = 640, height: 'int' = 400, actors=(), **camera_kw) -> 'dict' (to call the implementation directly, import drivehumanoid; drivehumanoid.world_camera_impostors(world: 'dict', pose, K, width: 'int' = 640, height: 'int' = 400, actors=(), **camera_kw) -> 'dict'; from the registry, opsdrive.get("world_camera_impostors"))
Captures the world with driveworld.world_camera and pastes the impostors of actors comparing front and back by depth.
actors = [{"imp": humanoid_impostors の返り値, "x", "y", "yaw", "distance" (歩いた距離 [m])}, …]. Heading step = the camera azimuth as seen from the body, rounded to n_yaw steps; phase = the step nearest to the remainder of the walked distance divided by the period. Scale = the actual camera's "pixels per 1 m" / the pre-render's "pixels per 1 m" (nearest-neighbour scaling). Returns the same keys as world_camera. Pasted pixels get label = the object's label (7), face = −2 (no triangle), shade = 1. In addition "impostor_pixels" (number of pasted pixels).
Empty input (world an empty dict) raises ValueError.
• 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_humanoids — py -3.11 examples/poc_driving_humanoids.py
table as input)course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same
humanoid)humanoid_clip_mesh · world_pose_humanoid · humanoid_impostors
*Provenance: drivehumanoid.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.