elevation_map — DRIVE walkterrain op

• Data kinds: points → depth

• Call: import fullseye as fs; fs.ledger.elevation_map(points, cell: 'float' = 0.05, agg: 'str' = 'max', bounds=None) (to call the implementation directly, import terrain; terrain.elevation_map(points, cell: 'float' = 0.05, agg: 'str' = 'max', bounds=None); from the registry, opsdrive.get("elevation_map"))

• Return value through the ledger: fullseye.ledger.elevation_map(...) returns only the declared out type depth (the underlying function also returns auxiliary values). When you need what was dropped, use fullseye.ledger.elevation_map.raw(...) or call terrain.elevation_map directly.

• GPU: none (CPU reference implementation only)

Usage

Bin a point cloud into a 2.5-D elevation grid.

> The detailed description below is the original text — the summary and the headings are translated.

Parameters

points : (N, 3) array of (x, y, z), z = height.

cell : grid resolution in world units.

agg : 'max' (canopy / obstacle-safe, default), 'min' (ground), or 'mean'.

bounds : optional (xmin, xmax, ymin, ymax); defaults to the data extent.

Returns (grid, extent) where grid[i, j] is the aggregated height of cell (row i = y, col j = x) and empty cells are nan. extent is (xmin, xmax, ymin, ymax).

空の入力(points が 0 要素)は bounds があれば全セル nan の格子を返す(理由: 観測の無い範囲は nan = 観測していない。bounds が無ければ範囲が決まらないので ValueError)。An empty cloud with bounds gives an all-nan grid; without bounds it raises ValueError (no extent).

References (sample data, literature)

• 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.

Runnable examples (verified samples that actually call this op)

• perception_pipeline — py -3.11 examples/perception_pipeline.py

• physical_ai_perception — py -3.11 examples/physical_ai_perception.py

• walking_ops_tour — py -3.11 examples/walking_ops_tour.py

Ops the type connects to (they accept depth as input)

spin_from_marker_sequence · carla_transform_matrix · carla_pose_to_world · carla_camera_pose · carla_xy_yaw · carla_scene_load · town_chain · osm_parse

Same category (walkterrain)

fill_gaps · elevation_traversability · foothold_score · ground_surface · ground_plane · detect_obstacles · fuse_elevation · roughness_map


*Provenance: terrain.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.