Instructions for Use
Support the classification and Instance Segmentation of the point cloud in the power scenario. Wherein, based on the deep learning capability, instance individuals such as power lines and towers in the point cloud in the power scene can be segmented, and the points belonging to the same instance have the same instance ID.
In addition, it supports the exclusion of points of specified categories from participating in Instance Segmentation operations, such as ground points and vegetation points, so as to effectively improve the efficiency of Instance Segmentation and reduce the demand for computer resources.
Before using this tool, you need to obtain the resource extension package first, and then configure the environment according to the description file in the extension package. The address for obtaining the extension package is: SuperMap official website -> Platform software download page-> SuperMap iDesktopX specific version-> the file containing Extension _ AI 3D in the product package name.
A Machine Learning extension license is required to use this tool.
Parameter Description
| Parameter Name | Parameter Description | Parameter Type |
|---|---|---|
| Point cloud file directory | Source Point Cloud Data storage path, currently only supports *.las format | String |
| Excluded Categories | Set Excluded category name and category numbers. For example, ground (ASPRS-defined number 2), vegetation (ASPRS-defined number 3, 4, or 5), undefined (ASPRS-defined number 0 or 1). Excluded category points will not participate in the Instance Segmentation operation. |
String |
| Output Storage Directory | Result Point Cloud Data (*.las) Save path | String |
Output Result
| Parameter Name | Parameter Description | Parameter Type |
|---|---|---|
| Point Cloud Instance Segmentation | Point Cloud Instance Segmentation Success | Boolean |