Target Object Selection and Recognition

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.

After point cloud preprocessing, select one or more bins from the target object editor for recognition.

If an external service is used to trigger the Mech-Visionproject to run, it is recommended to close the "3D Bin Recognition" tool before triggering the project.

If a project is triggered to run when the "3D Bin Recognition" tool is open, the content in the visualization window and the recognition result below will not be updated after option switching. Follow these steps:

  1. Close 3D Bin Recognition tool.

  2. Enable Debug Output.

  3. Reopen the 3D Bin Recognition tool.

After completing the above operations, switch the visualization options again to view the recognition result and visualization output normally.

Select Target Object

Follow these tips to update the bins in the target object editor to this tool, and then select the bin to recognize.

  • If there are no bins in the target object editor, select the operation workflow to create a bin. After configuring and saving the bin, click Update target object.

  • If there are configured bins in the target object editor, you can just click Update target object.

Adjust Recognition Parameters

Different recognition parameters need to be set according to different bin configuration workflows in the target object editor.

Calculate Bin Pose with 3D Matching

If the bin is configured in the target object editor by using the "Acquire point cloud using camera" or "Import STL file" workflow, you need to use 3D matching to calculate the bin pose. This method is suitable for recognizing bins whose top surfaces are irregular and partially occluded.

After selecting this method, you need to set the following parameters.

Parameter Description

Confidence threshold

Parameter description: If the confidence of a matching result is greater than this threshold, the result is considered valid. The higher the confidence, the more accurate the matching result.
Default value: 0.5000
Tuning instructions: It is recommended to first set this parameter to the default value and view the running result. If false recognition occurs, it is recommended to increase this parameter appropriately. If missed recognition occurs, it is recommended to decrease this parameter appropriately.

Calculate Bin Pose Directly

If the bin is configured in the target object editor by using the "No point cloud model required" workflow, the bin pose can be calculated directly. This method is suitable for bins whose top surfaces are regular and flat.

After selecting this method, you need to set the following parameters.

Parameter Description

Bin Dimensions

Parameter description: This parameter is used to set the length, width, and height of the bin.

Bin Pose Offset

Parameter description: This parameter is used to adjust the bin pose to the bin center.
Default value: 0.0000 mm
Tuning instructions: In general, this value should be set to half of the bin height. After adjusting this value, rerun the project for the parameter adjustment to take effect.

Check Recognition Result

After setting the above parameters, click Run Step or Run project to view the running result.

After bin recognition, click Next to enter the "General settings" process.

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.