Point Cloud Axial Merge
Description
This operator is used to merge multiple input point cloud clusters along a specified axis. It first calculates the center and size of each point cloud cluster, then sorts them along the specified "Merge Axis". It then iterates through the sorted point cloud clusters; if two adjacent clusters are close enough along the axis and sufficiently similar in size, they are merged into a larger cluster. This process continues until no more clusters can be merged.
Overview
Merges multiple input point cloud clusters along a specified axis, used to merge multiple fragments of the same object that have been over-segmented.
Scenarios
Merging multiple independent parts belonging to a group that are arranged along an axis into a whole. For example, merging all items detected on the same shelf layer into a "layer" entity.
Inputs and Outputs
Inputs |
Scene Point Cloud: The list of point clouds to be merged. |
Outputs |
Merged point cloud: Returns the list of point cloud clusters merged according to the specified axis and parameters. |
Parameters
Axial Distance Threshold
Description |
Set this value according to the actual gap size between parts of the object. |
Parameter Range |
[1, 5000], Default value: 50, Unit: mm |
Parameter Range |
Values/Range: [1, 5000] Default: 50 Unit: mm |
Axial Size Ratio Threshold
Description |
This parameter helps prevent a large object from being incorrectly merged with a small fragment next to it. |
Parameter Range |
[0, 1], Default value: 0.1 |
Parameter Range |
Values/Range: [0, 1] Default: 0.1 |
Merge Axis
Description |
Defines a 3D vector [x, y, z] as the directional reference for distance and size measurement. |
Tuning Instructions |
Sets the target direction for the merge operation. |
Parameter Range |
Default: [0, 0, 1] |
Minimum Cluster Points
Description |
Suitable for filtering out meaningless small noise clusters composed of a few points. Appropriately increase this value to ensure meaningful clustering results are output. |
Parameter Range |
[1, 4000000], Default value: 100 |
Parameter Range |
Values/Range: [1, 10000000] Default: 1000 |
Maximum Cluster Points
Description |
Suitable for scenarios where a very large background or support surface needs to be excluded. For example, to ignore a table and only analyze small objects on it, set an upper limit to filter out the largest point cloud cluster representing the table. |
Parameter Range |
[1, 4000000], Default value: 4000000 |
Parameter Range |
Values/Range: [1, 10000000] Default: 4000000 |
Sort Order
Description |
Sets the sorting rule for the output list of point cloud clusters. |
Tuning Instructions |
The operator calculates the position of the center point of each cluster on the "Clustering Axis" and sorts them based on this position. "Low to High" means sorting from the negative direction to the positive direction along the clustering axis, and vice versa for sorting from the positive direction to the negative direction. |
Parameter Range |
Values/Range:
Default: Low to High |
Keep All Results
Description |
Controls whether to output all segmentation results or only retain a portion for each input point cloud. |
Tuning Instructions |
Enabled (True): Default option, retains all clusters found that meet the point count limits. Disabled (False): Will only retain the top N largest clusters specified by the "Number of Results to Keep" parameter. |
Parameter Range |
Values/Range:
Default: True |
Number of Results to Keep
Description |
For each input point cloud, sorts the segmentation results by point cloud quantity from large to small, retaining the top few point clouds. For example, setting to 1 means retaining only the largest result, 2 means retaining the top 2 results, 3 means retaining the top 3 results, and so on. |
Parameter Range |
[1, 1000], Default value: 1 |
Parameter Range |
Values/Range: [1, 100] Default: 1 |