Transform 2D Pose

You are currently viewing the documentation for the latest version (2.2.2). 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 Description

This Step is used to perform pose reference frame transformation of the input 2D poses based on the object pose. The 2D pose obtained in the rectified/aligned image frame can be transformed back to the original image frame, and the 2D pose in the original image frame can also be transformed into the rectified/aligned image frame.

Usage Scenario

This Step is applicable to scenarios where an image is first rectified, aligned, or transformed, and then 2D poses are recognized in the transformed image.

Input and Output

Input

Input Port Data Type Description

Original Poses

Pose2D[]

The 2D poses to be transformed. Depending on the Transformation Type setting, the poses can be in the original image frame or the rectified image frame.

Alignment Parameter Group

Pose2D[]

Optional input. Provides the translation and rotation parameters required to align the matched object with the template.

Output

Output Port Data Type Description

Transformed Poses

Pose2D[]

The transformed 2D poses. The output frame is determined by the Transformation Type setting. The output poses can be in the rectified image frame or transformed back to the original image frame.

Parameter Description

Parameter Description

Transformation Type

Sets the frame transformation type for the 2D poses.

Value List:

  • Original Image to Rectified Image: Transforms 2D poses in the original image frame to the rectified image frame. This option is applicable to scenarios where original 2D poses need to be used in the rectified image.

  • Rectified Image to Original Image: Transforms 2D poses in the rectified image frame back to the original image frame. This option is applicable to scenarios where 2D recognition is performed in the rectified image and the original image calibration parameters need to be used for subsequent processing.

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.