Point Cloud Segmentation

Summary

The TLS point cloud segmentation method (originally developed by Tao et al.,2015) utilizes a bottom-up approach to identifying individual trees. This is because TLS data is typically acquired beneath the canopy where tree stems can be readily observed and used to inform the segmentation algorithms that delimit the spatial extents of individual trees within a forest or stand. Individual Tree attributes, including Tree Height and Diameter at Breast Height (DBH), can be then determined for each tree segmented out of the input TLS dataset.

Usage

Navigate to and click on TLS Forest > Point Cloud Segmentation.

Point Cloud Segmentation

Settings

  • Input Data: Ensure that each input point cloud data is Normalize by DEM or Normalize by Ground Points.
  • From Class: Classes which participate in the point cloud segmentation (all classes by default).
  • Cluster Tolerance (meter)(default value is "0.2"): Users can control the accuracy and efficiency of the individual tree segmentation process by changing this value. Increase of this threshold will result in higher efficiency of the individual tree segmentation process. But if this threshold is too large, it will lower accuracy.
  • Minimum Cluster Size:This parameter will influence the growing of point cloud of individual tree's crown. Fewer points will lead to higher accuracy and lower efficiency. Vice versa.
  • Maximum DBH (meter)(default value is "1.4"): Upper DBH threshold for fitting DBH.
  • Minimum DBH (default value is "1.2"): Lower DBH threshold for fitting DBH.
  • Height Above Ground (meter)(default value is "0.3"): Only the points above this height will be involved in individual tree segmentation. This parameter is used to decrease the influence of ground points and weeds to the segmentation. It will influence the accuracy of the detection of trunk, if this value is too large.
  • Minimum Tree Height (meter)(default value is "2"): Lower threshold of an object which could be recognized as a tree. This is used for filtering out small trees based on the growth rate of the region.
  • Trunk Height (meter)(default value is "1.6"): the algorithm will extract the points in the range between Height Above Ground and Trunk Height, and detect the trunk used as the starting point of growing of point could. It is suggested that this value should be less than the height of the lowest branch.
  • 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.
  • Output Path: Path of the output file, which is a comma-separated database table in the .csv format containing the ID of each individual tree identified during the segmentation process, the x, y coordinate of each individual tree, individual tree heights, DBHs, crown diameters, crown areas, and crown volumes. Please refer to Individual Tree Segmentation Result File Format in the appendix.Please refer to View the Point Cloud Segmentation Results for the steps to view the results.
  • DefaultValue: Reset each parameter to the default value.
    @inproceedings{
        author={Tao S L, Wu F F, Guo Q H, Wang Y C, Li W K, Xue B L, Hu X Y, Li P, Tian D, Li C,Yao H, Li Y M, Xu G C and Fang J Y},
        title={Segmentation tree crowns from terrestrial and mobile LiDAR data by exploring ecological theories},
        booktitle={ISPRS Journal of Photogrammetry and Remote Sensing,110:66-76},
        year={2015}
    }

results matching ""

    No results matching ""