japan op• Data kinds: table → table
• Call: import fullseye as fs; fs.ledger.japan_world(graph: 'dict', *, step: 'float' = 0.5, kerb_height: 'float' = 0.15, kerb_width: 'float' = 0.3, ground_step: 'float' = 2.0, margin: 'float' = 6.0, buildings=None, props: 'bool' = True, pole_pitch: 'float' = 30.0, lines: 'bool' = True, tolerance_px: 'float' = 0.75, side: 'str' = 'left') -> 'Dict[str, object]' (to call the implementation directly, import drivejapan; drivejapan.japan_world(graph: 'dict', *, step: 'float' = 0.5, kerb_height: 'float' = 0.15, kerb_width: 'float' = 0.3, ground_step: 'float' = 2.0, margin: 'float' = 6.0, buildings=None, props: 'bool' = True, pole_pitch: 'float' = 30.0, lines: 'bool' = True, tolerance_px: 'float' = 0.75, side: 'str' = 'left') -> 'Dict[str, object]'; from the registry, opsdrive.get("japan_world"))
Builds a 3-D world of a Japanese town (driveworld format) from the road network.
Road surface = a grid plane over the whole area (z 0, label 0). The holes in the union of the roads = blocks: the sidewalk surface (z = kerb_height, label 15) and a kerb strip (label 1). Kerbs on the outer edge too. Lane markings (label 9): on two-lane two-way roads the centre line is a white dashed line (5 m / 5 m), on four or more lanes a solid line, lane boundaries are dashed. At intersections the markings are cut back by the half-width of the other edges. With props, from node features: traffic signals (traffic_signals, per entering edge, on the far side of the intersection, on the left), pedestrian crossings (crossing, 0.45 m stripes parallel to the direction of travel, label 12), stops (stop / give_way: sign + stop line + the "TOMARE" (stop) road marking, per entering edge), level crossings (level_crossing: 2 rails (label 8) + level-crossing warning sign + stop line). On residential roads (residential / unclassified / living_street), utility poles (label 16) at pole_pitch intervals along the edge on the travel side. If buildings = the list of buildings from plateau_parse, extruded prisms (label 14). Return value = a driveworld world + {"graph", "roadmask", "loops", "signals": [{"node", "edge", "object", "pose"}], "stats": {...}}. Raises ValueError: side other than left/right, invalid kerb/step.
Empty input (graph is 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_japan_town — py -3.11 examples/poc_driving_japan_town.py
table as input)course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same
japan)osm_synthetic · osm_parse · osm_road_graph · osm_road_mask · osm_road_loops · osm_route · japan_stats · latlon_to_local
*Provenance: drivejapan.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.