跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
浏览器与自动化

point-cloud-lidar

LiDAR and point cloud processing: PDAL pipelines, LAS/LAZ/COPC handling, ground classification, DTM/DSM/CHM generation, canopy and building metrics, and photogrammetric (SfM) point clouds. Use when the primary input is LAS, LAZ, COPC, LiDAR, or an unstructured 3D point cloud. This skill owns vertical datum agreement, co-registration and the vertical-accuracy budget when two acquisitions are differenced with comparability not yet established; once datum, geoid and accuracy are documented, a subsidence or elevation-change question is change-detection's. Route a derived DEM, DTM, DSM or CHM to terrain-hydrology unless point-level classification, comparability, or metrics remain in scope.

Muhammed Enes Duran · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add muend/geoai-skills --skill point-cloud-lidar

技能说明


name: point-cloud-lidar description: >- LiDAR and point cloud processing: PDAL pipelines, LAS/LAZ/COPC handling, ground classification, DTM/DSM/CHM generation, canopy and building metrics, and photogrammetric (SfM) point clouds. Use when the primary input is LAS, LAZ, COPC, LiDAR, or an unstructured 3D point cloud. This skill owns vertical datum agreement, co-registration and the vertical-accuracy budget when two acquisitions are differenced with comparability not yet established; once datum, geoid and accuracy are documented, a subsidence or elevation-change question is change-detection's. Route a derived DEM, DTM, DSM or CHM to terrain-hydrology unless point-level classification, comparability, or metrics remain in scope. license: MIT metadata: author: Muhammed Enes Duran

Point Clouds & LiDAR

Purpose: from raw returns to defensible elevation and structure products. The recurring failure modes: trusting vendor classification blindly, mixing return types in surfaces (DSM from last returns, DTM with vegetation), and ignoring point density when choosing output resolution.

First contact with any cloud

pdal info input.laz --summary        # counts, bounds, CRS, classes, returns

Report before touching anything: point count, density (pts/m² — decides achievable raster resolution), CRS (horizontal AND vertical datum — ellipsoidal vs orthometric heights differ by the geoid undulation, tens of meters in places), classification present?, return numbers present?, flight-line overlap artifacts. A cloud without CRS metadata: resolve from the provider, never assume.

Format and scale

FormatUse
LAZCompressed interchange/archive — default
COPC (cloud-optimized LAZ)Streaming/HTTP range access, web viewers
LASOnly when a tool can't read LAZ
Entwine/EPTMassive multi-tile collections, indexed

Tile large collections; process per-tile with buffered edges (~2× search radius) to avoid seam artifacts in filters and surfaces; drop the buffer on write.

PDAL pipeline pattern

{
  "pipeline": [
    "input.laz",
    {"type": "filters.reprojection", "out_srs": "EPSG:32636"},
    {"type": "filters.outlier", "method": "statistical",
     "mean_k": 8, "multiplier": 2.5},
    {"type": "filters.smrf", "slope": 0.15, "window": 18.0,
     "threshold": 0.5, "scalar": 1.2},
    {"type": "writers.las", "filename": "classified.laz",
     "extra_dims": "all"}
  ]
}

Run: pdal pipeline pipeline.json. Denoise BEFORE ground classification (low outliers below ground destroy SMRF/CSF); tune slope up for steep terrain, window to the largest non-ground object (big buildings need bigger windows).

Ground classification & DTM

  • If vendor class 2 (ground) exists: audit it on 2-3 cross-sections (bridges, dense canopy, steep slopes) before trusting; reclassify where it fails.
  • Algorithms: SMRF (PDAL default, robust), CSF (cloth simulation, good in steep forest). Parameters are terrain-dependent — show a cross-section plot as evidence, not just the parameter list.
  • DTM from ground-only points; interpolation: TIN → raster (standard for DTM) or IDW for dense clouds. Output resolution ≥ ~1/√density; a 0.5 m DTM from 1 pt/m² data is invented detail.
  • DSM from first returns / highest-point binning. CHM = DSM − DTM, clamp negatives to 0, and use a pit-free algorithm for forestry (naive CHMs are pocked by within-crown pits).

Structure metrics

  • Forestry: height percentiles (p95 ≈ canopy height), canopy cover (first returns > 2 m / all first returns), density metrics per grid cell or plot; normalize heights against the DTM first (filters.hag_dem or filters.hag_nn). Individual tree detection: local maxima on pit-free CHM + watershed segmentation — validate count against field plots or manual photo-interpretation samples.
  • Buildings: class 6 or planar-patch extraction; building height = p90(roof points HAG); footprint fusion with cadastre/OSM polygons via zonal statistics on HAG.
  • Downstream terrain analysis (slope, watersheds) → terrain-hydrology; DL on point clouds or derived rasters → geo-deep-learning.

SfM/photogrammetric clouds — not LiDAR

Drone photogrammetry clouds have no returns, no canopy penetration (ground under vegetation is guessed), correlated noise, and possible doming from poor camera calibration. A "DTM" from SfM over forest is a canopy model. State the sensor type in every deliverable; use LiDAR-specific claims (penetration, return metrics) only for LiDAR.

Vertical datum: resolve, transform, record

Every elevation product carries three obligations, and the third is the one that gets skipped. Stating the datum in your answer is not recording it. A height product whose vertical datum lives only in a chat reply is indistinguishable from one with no datum at all the moment the file is handed to anyone else.

  1. Resolve. Read the vertical CRS from the header/VLR. Where it is missing or contradicted, resolve it against acquisition metadata (vendor flight report, project spec) or diagnose it: a tile-wide constant offset matching the local geoid undulation is the ellipsoidal-vs-orthometric fingerprint. Never infer a datum from elevation magnitude alone.
  2. Transform. Apply an explicit, named transformation — a compound CRS plus geoid model through filters.reprojection, or a fitted per-tile offset when no geoid grid is available. Re-difference the overlaps afterwards and confirm strips agree within noise.
  3. Record it into the output, not just the reply. Every delivered product must carry, in machine-readable form:
    • the compound or vertical CRS written into the file itself (LAS/LAZ header VLR, GeoTIFF CRS, or PROJJSON in the sidecar);
    • the geoid model name and version actually applied (e.g. EGM2008, GEOID18) and the transformation pipeline or EPSG operation co
阅读完整来源 ↗