LIDAR_CLASSIFY_GRAPH

The LIDAR_CLASSIFY_GRAPH command allows for automatically identifying and classifying building/high vegetation points from Lidar point clouds using a segmentation method. The following parameters are supported by the command:

  • FILENAME - filename or description of loaded layer(s) to classify Lidar points in. This parameter can be listed more than once to specify multiple input files, like FILENAME="FILENAME_1" FILENAME="FILENAME_2".
  • TYPE - specifies what type(s) of points to classify. If you don't provide a TYPE parameter only ground points will be classified. To classify multiple types, provide a comma-separated list, like TYPE="BUILDIN, HIGH_VEG". The following values are valid:
    • BUILDING - Classify building points
    • HIGH_VEG - Classify high vegetation points
  • GRID_BIN_SIZE -specifies the gating distance for the local neighborhood used in principal component analysis. For example a value of GRID_BIN_SIZE="3.0" would make each local neighborhood 3 times the calculated native spacing of the point data. This is the same as the 'Neighborhood Range' setting within the dialog of the classification tool. If you want to specify a spacing in meters rather than as a multiple of the native spacing for the point cloud, use a negative value (-). For example, to get a spacing of 0.6 meters, use GRID_BIN_SIZE="-0.6".
  • LIDAR_RESET_NON_GROUND - specifies that any points that are already marked as one of the types being classified should be reset to unclassified at the start of the operation. Add LIDAR_RESET_NONGROUND=YES to reset the points.
  • LIDAR_MIN_HEIGHT - specifies the minimum height above ground that a point has to be in order to consider it as a possible building or high vegetation point.
  • LIDAR_MAX_NUM_NEIGHBORS - Maximum number of neighbors used in principal component analysis. Allows for reduction in computational cost in the case that points are densely packed.
  • LIDAR_MAX_STD_DEV - Point-to-point associations used for clustering are limited to those that are within a specified statistical distance. This threshold reduces processing requirements and maintains the purity of clusters in the sense that it inhibits associations with points that have very different local neighborhood characteristics. A good value for this is generally around 3-4 with larger values required for data that is noisy, striped or has other measurement related problems. If this parameter is too small, then little or no clustering will happen and there will be a low probability of detection. If this parameter is too large, then clustering may be overly permissive and there will be a high probability of false alarm.
  • LIDAR_MIN_CLUSTER_SIZE - The minimum number of points required in a cluster based on similar principal component analysis statistics for the cluster to be classified.

SAMPLE

GLOBAL_MAPPER_SCRIPT VERSION=1.00
UNLOAD_ALL
LOG_MESSAGE Script <%SCRIPT_FILENAME%> started at %DATE% %TIME%
DEFINE_VAR NAME="LASFILE" VALUE="Augusta_LiDAR.laz"
DEFINE_VAR NAME="DATA_DIR" VALUE="C:\Users\ChrisSmith\src\GMTrunk\geoStats\test\data\"
SET_LOG_FILE FILENAME=".%LASFILE%.log" APPEND_TO_FILE=NO

IMPORT FILENAME="%DATA_DIR%%LASFILE%"

LIDAR_CLASSIFY FILENAME="%LASFILE%"\
TYPE=GROUND\
GRID_BIN_SIZE=3.0\
LIDAR_RESET_GROUND=YES\
LIDAR_CURVATURE=0.3\ LIDAR_MAX_HEIGHT_DELTA=50.0\ LIDAR_SLOPE=2.0 LIDAR_CLASSIFY_GRAPH FILENAME="%LASFILE%"\ GRID_BIN_SIZE=4.0\ TYPE=BUILDING,HIGH_VEG\ LIDAR_RESET_NON_GROUND=YES\ LIDAR_MIN_HEIGHT=2.0\ LIDAR_MIN_NUM_NEIGHBORS=3\ LIDAR_MAX_NUM_NEIGHBORS=64\ LIDAR_MAX_STD_DEV=3 LIDAR_EXTRACT FILENAME="%LASFILE%"\ GRID_BIN_SIZE=4.0\ TYPE=BUILDING\ LIDAR_MIN_POINTS_IN_PLANE=20\ LIDAR_MAX_DISTANCE_TO_PLANE=0.5\ LIDAR_MIN_FOOTPRINT_AREA_SQM=20\ LIDAR_PSEUDOMEASUREMENTS_AT_PLANAR_INTERSECTIONS=YES\ LIDAR_SIMPLIFICATION_EPSILON=1\ LIDAR_CREATE_FOOTPRINTS=YES\ LIDAR_CREATE_SIDEWALLS=YES\ LIDAR_CREATE_SEPERATE_ROOF_PLANES=YES\ LIDAR_CREATE_BUILDINGS_AS_MESH=YES\ LIDAR_COLOR_VERTICES=NO SAVE_WORKSPACE FILENAME=".%LASFILE%.gmw"