Point Cloud Segmentation from Seed Points


This function supports batch processing of multiple files. The input data includes normalized point cloud data and the corresponding seed points file. For the generation of seed points file please refer to Generate Seed Points from CHM and Generate Seeds from Layer Stacking.


Navigate to and click on ALS Forest > Segmentation > Point Cloud Segmentation from Seed Points.



  • From Class: Classes which participate in the PCS with seeds (all classes by default).
  • Input Data: Ensure that each input point cloud data is Normalize by DEM or Normalize by Ground Points.
  • Point Cloud File: Click to select the point cloud data to be processed.
  • Seed File: Click to select the seed file.
  • : Five datasets can be processed in batch by default. Click to add more files to be processed.
  • : Delete the selected point cloud and seed points file.
  • : Clear the file list.
  • Height Above Ground (meter)(default value is "2"): Point cloud data above this value will be divided into single trees. To split low trees, set this value to be smaller than the minimum tree height to be divided.
  • Optimize color rendering for individual tree segmentation result (checked by default): By reorganizing the tree ID generated after the individual tree segmentation, it can greatly solve the problem of rendering the same color to the trees next to each other. Note: if choosing to optimize the color rendering, the tree IDs in new csv file for individual tree segmentation are not one-to-one correspond to those in the input seeds files.
  • Output Path: Path of the output file. The output product is a comma-separated table in the .csv format which contains the ID of each tree, the x, y coordinate locations, the tree height, the crown diameter, the crown area and the crown volume. Refer to ALS point cloud segmentation results.
  • DefaultValue: Restore the default parameters.

To view the segmentation results, please refer to View the Point Cloud Segmentation Results.

results matching ""

    No results matching ""