Point Cloud Preprocessing

You are currently viewing the documentation for the latest version (2.1.2). 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

This Step performs pre-processing operations such as point filtering, point cloud merging, and image filtering on the original point cloud to delete interfering points, thus speeding up the processing of subsequent Steps.

Usage Scenario

This Step typically follows the Capture Images from Camera Step to optimize the original point cloud and improve the processing speed of subsequent Steps.

Input and Output

  • Input:

    1. Depth map.

    2. 2D image that provides texture information for the point cloud (optional).

  • Output:

    1. Surface point cloud in the ROI.

    2. Edge point cloud in the ROI.

    3. Textured scene point cloud (usually used for path planning).

Parameters

3D ROI

Instruction: Click the Open the editor button and set the 3D ROI in the “Set 3D ROI” window. For detailed instructions, please refer to Set 3D ROI.

Noise Removal Level

Description: This parameter is used to determine the noise removal level.

Value list: None, Weak, Strong, Customized

Default value: Strong

Instruction: This parameter should be adjusted when there is severe noise or erroneous burrs on the edges of the point cloud of the target object. The stronger the removal level, the better the noise removal effect.

Edge Extraction Effect

Description: This parameter is used to determine the edge extraction effect.

Value list: Fine, Standard, Rough, Extra Rough, Customized

Default value: Standard

Instruction: If the edge extraction effect on the target object is not satisfactory, adjust this parameter. The finer the detection, the richer the edge line details. The rougher the detection, the more local edge details will be discarded. However, please retain sufficient and stable target object features to ensure the correctness of the recognition results.

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.