Point Cloud Organization
Function Description
Utilizes Camera internal reference to convert the input, usually unordered, camera coordinate system Pointcloud into an Ordered Point Cloud.
The converted Pointcloud forms a two-dimensional grid in structure, and the three-dimensional points in the original Pointcloud will be mapped to the corresponding positions of this two-dimensional grid.
If some positions in the grid do not have corresponding three-dimensional points in the original Pointcloud, these positions will be marked as invalid values (NaN).
Usage Scenarios
-
Align with 2D Image : Associate 3D Pointcloud data with 2D Image captured by the same camera from the same perspective at the pixel level. For example, find the corresponding depth value or 3D coordinates for each pixel of the Image, or assign Image colors to the Pointcloud.
-
Generate Depth Map : The Z-coordinates (depth information) in the Ordered Point Cloud can be directly extracted or transformed to generate a depth map aligned with the reference Image.
-
Apply 2D Image Processing Algorithms : Certain algorithms designed for 2D Image, such as filtering and feature extraction, can be applied to the transformed data structure after Pointcloud organization (e.g., applying 2D mean filtering to the depth values of the Ordered Point Cloud).
Input/Output
Input Items |
Image: Reference Image. Camera Coordinate System Pointcloud: A list of one or more Pointclouds. Camera internal reference: In-camera reference matrix. |
Output Items |
Organized Pointcloud: Pointcloud processed through organization. If the input is a Point Cloud List, the output will also be a list of organized Pointclouds corresponding to each input Pointcloud. |
Parameter Description
This operator has two versions:
Both have identical core functions and parameters, differing only in the type of Pointcloud data processed. |
Merge input point clouds
Parameter Description |
Controls whether to first Merge input point clouds into a single, large Pointcloud when the input is a Point Cloud List, before performing the organization process. |
Parameter Tuning Guide |
|
Align Image Dimensions
Parameter Description |
This parameter controls whether the 2D dimensions (width and height) of the output Ordered Point Cloud strictly match the input Image dimensions. |
Parameter Tuning Guide |
|