Convert 2D Points to 3D Points

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 converts 2D images and corresponding poses to 3D point clouds.

Usage Scenario

This Step is suitable for scenarios where the quality of the point cloud actually acquired by the camera is poor. This Step combines 2D images (such as object masks detected by deep learning, object edges detected by 2D images, etc.) with their corresponding poses to generate the corresponding 3D point cloud data.

Input and Output

Input

Input port Data type Description

Images

Image []

Images input to this port will be converted to point clouds.

Poses

Pose []

Poses input to this port will be used to convert the images to point clouds.

Output

Output port Data type Description

Point cloud

PointCloud []

3D point clouds obtained by transforming the input 2D images by the input poses.

Parameter Description

Parameter Description

Calc Normal

Description: Once this parameter is selected, the normals of the output point cloud will be calculated.

Default setting: Unselected

Search Radius

Description: This parameter is the neighborhood size used for calculating normals. Select Calc Normal to set this parameter.

Default value: 10.0000

Iterations

Description: This parameter is the maximum number of iterations for calculating normals. Select Calc Normal to set this parameter.

Default value: 100

Error Tolerance

Description: This parameter is the error tolerance of the RANSAC algorithm for calculating normals. If the value is set too small, too few points will be used to calculate normals, and if the value is set too large, more noise will be introduced. Both of the above conditions may lead to inaccuracy in normal calculation. Select Calc Normal to set this parameter.

Default value: 1.0000

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.