Transform Point Clouds

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 can transform point clouds from one reference frame to another, or transform within its own reference frame according to the reference pose.

transform point clouds functional description

Usage Scenario

This Step is usually used to transform point clouds between camera reference frame and robot reference frame.

If you are using a truss robot, please use the Transform Point Clouds for Truss Step.

Input and Output

Input

Input port Data type Description

Original Point Clouds

PointCloud/XYZNormal[]

Point clouds to transform.

Reference Pose

Pose[] -

Reference poses (optional, input when the parameter "Transformation Type" is set to "AllWithFirst", "FirstWithAll", or "UseCorrespondenceInput", under which a point cloud will be transformed to the reference frame of the corresponding reference pose).

Transformation Matrix

Matrix4D[] -

Affine matrix (optional, input when the parameter "Transformation Type" is set to "AffineTransform", under which the point cloud will be transformed based on the affine matrix).

Output

Output port Data type Description

Transformed Point Clouds

PointCloud/XYZNormal[]

Point cloud of the highest-layer target objects.

Parameters

Transformation Settings

Parameter Description

Transformation Type

Parameter description: This parameter is used to select the type of point cloud transformation.

Default setting: CameraToRobot.

Options: CameraToRobot, RobotToCamera, AllWithFirst, FirstWithAll, UseCorrespondenceInput, and AffineTransform.

Instructions:

  • CameraToRobot: Transform the point clouds from the camera reference frame to the robot reference frame. Please refer to the tuning example for the corresponding result.

  • Robot to camera: Transform the point clouds from the robot reference frame to the camera reference frame. Please refer to the tuning example for the corresponding result.

  • All with first: Transform the original point cloud to the reference frame of the first input reference pose. Please refer to the tuning example for the corresponding result.

  • First with all: Transform the first original point cloud to the reference frame of each reference pose in the input pose list, respectively. Please refer to the tuning example for the corresponding result.

  • UseCorrespondenceInput: Transform the original point clouds to another reference frame according to the corresponding reference poses respectively. Please refer to the tuning example for the corresponding result.

  • AffineTransform: Transform the point clouds with an affine matrix. The pose list should be converted to matrix4D format with the Step From PoseList to Matrix4D first and then input. Please refer to the tuning example for the corresponding result.

Examples

CameraToRobot

The following figure shows the results before (left) and after (right) point cloud transformation of CameraToRobot.

transform point clouds camera to robot 1

RobotToCamera

The following figure shows the results before (left) and after (right) point cloud transformation of RobotToCamera.

transform point clouds robot to camera 1

AllWithFirst

The following figure shows the results before (left) and after (right) point cloud transformation of AllWithFirst.

transform point clouds all with first 1

FirstWithAll

The following figure shows the point-cloud transformation result of FirstWithAll.

transform point clouds first with all 1

UseCorrespondenceInput

The following figure shows the point-cloud transformation result of UseCorrespondenceInput.

transform point clouds use correspondence input 1

AffineTransform

The following figure shows the point-cloud transformation result of AffineTransform.

transform point clouds affine transform

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.

  • Preference
  • I accept
  • I don't accept