🟠 Extract Point Cloud from Mask List
Function Description
This operator extracts point clouds from regions covered by each mask from a corresponding ordered point cloud based on one or more input binary mask images. It traverses the input mask list, generates an independent point cloud for each mask, and finally outputs these point clouds in list form.
Usage Scenarios
After generating masks through image processing, this operator can be used to convert these 2D regions into corresponding 3D point clouds.
Input Output
Input |
Point cloud: Ordered point cloud whose dimensions must be consistent with the input mask images. Detection result mask image list: A list composed of one or more binary mask images. |
Output |
Masked point cloud list: A point cloud list where each point cloud element corresponds to one mask in the input mask list. |
Parameter Description
|
This operator has two versions:
Both have identical core functionality and parameters, differing only in the type of point cloud data they process. |
Minimum Bounding Box
Parameter Description |
Extracts point clouds based on the minimum oriented bounding box of detection instances. Suitable for scenarios where object shapes are relatively regular, capable of enclosing targets with minimal rectangles. |
Parameter Adjustment |
|
Mask
Parameter Description |
Directly uses the precise pixel regions of masks to extract point clouds. High precision, capable of precisely extracting point clouds of arbitrarily shaped objects. |
Parameter Adjustment |
|
Min Max Values
Parameter Description |
Extracts point clouds based on axis-aligned bounding boxes (horizontal and vertical rectangles) of detection instances. Fastest computation speed, suitable for scenarios where precision requirements for extraction regions are not high. |
Parameter Adjustment |
|
Central Circular Region
Parameter Description |
Mainly used to extract central point clouds for calculating point cloud center positions and normals. |
Parameter Adjustment |
Circle radius ratio: Defines the radius of the circular region, which is a proportion of the short side length of the detection instance bounding box. The larger the value, the larger the extracted circular region. If you want to obtain the core region of an object, you can use a smaller value; if you want to cover most of the object, increase this value. |