Estimate Point Cloud Edges by 2D Method

You are currently viewing the documentation for the latest version (2.2.0). To access a different version, click the "Switch version" button located in the upper-right corner of the page.

■ If you are not sure which version of the product you are currently using, please feel free to contact Mech-Mind Technical Support.

Function

This Step extracts the edges of the input point cloud.

estimate point cloud edges by 2d method estimate point cloud edges by 2d method

This Step projects the input 3D point cloud into a 2D image and generates the corresponding mask. Then, the contour detection and morphological processing is performed on the mask. Finally, the detected 2D contour is mapped back to the 3D point cloud and the edge of the point cloud is output.

Usage Scenario

This Step is usually used in the loading scenarios of flat workpieces to extract the point cloud edges of flat target objects. It is usually used with Steps related to 3D matching. This Step is faster than 3D Edge Extraction. It is recommended to use it for projects requiring short cycle times, with large quantities of 3D point cloud interference, and only requiring extracting the outermost edge points of the target object point clouds.

Input and Output

Input

Input port Data type Description

Point Clouds

PointCloud/XYZNormal []

Point clouds input to this port will have edges extracted.

Output

Output port Data type Description

Point Cloud Boundary

PointCloud/XYZNormal []

List of edge point clouds.

Parameter Description

Contour Settings

Parameter Description

2D Line Width

Description: This parameter is used to set the line width when extracting the contour on the mask. The larger the value, the thicker the generated 2D profile, and the more points it contains after being mapped to the edge of the 3D point cloud.
Default value: 3 px
Instruction: If the edge is thin, you can decrease the value; if the edge is discontinuous or fractured, you can increase the value.

Contour Search Method

Description: This parameter specifies the retrieval method of the contours and determines the contour range and hierarchy used for edge extraction, thus affecting the integrity of the generated edge point cloud and its contour structure.

Value list: CV_RETR_EXTERNAL, CV_RETR_LIST, CV_RETR_CCOMP, CV_RETR_TREE

  • CV_RETR_EXTERNAL: Retrieve only the outermost contour. Suitable for scenarios where only the contours of the target objects are involved.

  • CV_RETR_LIST: Retrieve all contours without establishing any hierarchical relationship. Suitable for scenarios that require all contours but do not care about the nesting relationship of the contours.

  • CV_RETR_CCOMP: Retrieve all contours and organize them into a two-level hierarchy (outer and inner contours).

  • CV_RETR_TREE: Retrieve all contours and reconstruct the complete hierarchy of the nested contours.

Default value: CV_RETR_EXTERNAL

Min Length

Description: This parameter is used to set the minimum number of pixels in the mask of the contour that is considered valid. Only contours with point count values greater than this value will be retained.
Default value: 20 px
Instruction: If there are many small noises in the scene, you can increase the value appropriately; if you need to preserve small edge details, you can decrease the value.

Merge Contours in the Same Point Cloud

Description: This parameter is used to determine whether to merge multiple profiles belonging to the same point cloud into one profile. After merging, the edge structure can be simplified; otherwise, all individual contours will be retained.
Default setting: Unselected

Custom Contour Hierarchy

Description: This parameter specifies the contour hierarchy to be extracted. This parameter should be set when the “Contour Search Method” is set to “CV_RETR_TREE”. The hierarchy grows from outer to inner layers. The outermost layer is 1. In addition, 0 indicates the contours of all layers, and -1 indicates the innermost layer.
Default value: 0

Morphological Operation Settings

Parameter Description

Dilate Kernel Size

Description: This parameter is used to set the range for dilation. It can fill small holes in masks or connect noise-induced separation areas. The larger the value, the more obvious the expansion effect.
Default value: 3 px

Erode Kernel Size

Description: This parameter is used to set the size of the erosion range, which can shrink the mask area and remove isolated noise or small protrusions. The larger the value, the more obvious the contraction effect.
Default value: 3 px

Is this page helpful?

You can give a feedback in any of the following ways:

We Value Your Privacy

We use cookies to provide you with the best possible experience on our website. By continuing to use the site, you acknowledge that you agree to the use of cookies. If you decline, a single cookie will be used to ensure you're not tracked or remembered when you visit this website.