3D Fine Matching Lite

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 is a lite version of 3D Fine Matching, in which the parameter configuration can be more intuitive.

This Step accurately matches the point cloud model and the scene point cloud and outputs the pose of the target object.

Usage Scenario

The 3D Coarse Matching V2 Step should be used before this Step to output the original candidate poses. Then, this Step will match the original poses more accurately and output the accurately calculated object poses.

Input and Output

Input

Input port Data type Description

Point Cloud (with normals)

PointCloud/XYZ-Normal[]

Objects in the scene point cloud input at this port will have their poses calculated through 3D fine matching. This scene point cloud is usually the same as the input to Step "3D Coarse Matching V2".

Coarsely Calculated Poses

Pose[]

This port takes the poses output by Step "3D Coarse Matching V2".

Output

Output port Data type Description

Object Center Points

Pose[]

Output the target object poses after fine matching.

Object Point Clouds (with normals)

PointCloud/XYZNormal[]

Point cloud of objects rendered from the point cloud model and the calculated object poses.

Pose Confidence Values

Number[]

Output the list of confidence values of the corresponding object poses.

Parameters

Parameter Description

Parameter Tuning Level

Parameter description: This parameter is used to select the Parameter Tuning Level for the Step.
Value list: Basic and Advanced.
Default value: Basic

Basic Parameter Tuning Level

Model Settings

Parameter Description

Select Target Object

Description: This parameter is used to select the target object that is configured in the target object editor.
Tuning instruction: After making a point cloud model with the target object editor, click the button to the right of the parameter to expand the drop-down list to select or switch the point cloud model file.

Matching Method Settings

Parameter Description

Matching Mode

Parameter description: This parameter is used to select between Edge Matching and Surface Matching modes.

Value list: Surface matching, Edge matching.

Default value: Surface matching.

Tuning recommendation: When the surface of the object has obvious recognizable features (such as crankshafts, rotors, and steel rods), it is recommended to use surface matching. You should create a point cloud model that represents the surface features of the object. When the object is relatively flat and shows clear and regular edge features under the camera (such as panels, track pads, connecting rods, and brake discs), it is recommended to use edge matching. You should create a point cloud model that represents the edge features of the object.

The value of Match Mode must be consistent with the model type (Surface model or Edge model) specified by the Select Target Object parameter. For example, if the matching mode is surface matching, the model specified by the Select Target Object parameter must also be a surface model.

Deviation Correction Capacity

Parameter description: This parameter is used to set the intensity of the deviation correction to the matching result from 3D Coarse Matching V2. The greater the deviation correction capacity is, the more likely the coarsely matched poses can be corrected to the accurately matched poses. Please note that an excessive deviation correction capability may lead to a loss of matching accuracy.
Value list: Small, Medium, and Large.
Default value: Small (applicable to most cases).
Tuning recommendation: When there is a relatively large deviation of the matching result, please adjust the Deviation Correction Capacity first. If the deviation is too large to be corrected by this parameter, please adjust the parameters in the 3D Coarse Matching V2 Step.

Operation Approach

Parameter description: This parameter specifies the operation approach of the matching process. The operation approach determines the relationship between the matching accuracy and matching speed. The higher the matching accuracy is, the longer the time required is.
Value list: High speed, Standard, High accuracy, and Extra high accuracy.
Default value: Standard.
Tuning recommendation: Please select the operation approach according to the actual requirement.

Validation Settings

Parameter Description

Confidence Threshold

Parameter description: This parameter is used to determine whether the matching result is valid. If the confidence of the matching result is above the threshold, the matching result is valid. The higher the confidence value is, the more accurate the matching result is.
Default value: 0.300

Only Consider Visible Surface of Model

Parameter description: This parameter is used to determine whether to only consider the visible part of the surface point cloud model in the matching process. You should set this parameter when the matching mode is Surface Matching. Once this parameter is selected, only the visible part of the surface point cloud model will be considered, which facilitates the calculation and produces a more reasonable matching confidence.
Default value: Unselected.
Tuning recommendation: It is recommended to select this parameter for object models that have parts not visible to the camera under a viewing angle, such as the complete point cloud model of a cylindrical object. For object models that are completely visible from the same viewing angle, such as the surface point cloud model of the upper side of a brake disc, this parameter can be ignored.

Result Validation Degree

Description: This parameter is used to select the degree of strictness applied when validating the matching results.
Default value: Standard.
Value list: Low, Standard, High, Ultra-high, Compatibility, Custom.
Tuning recommendation: In general, “Standard” is recommended. When the point cloud model is highly similar to the scene point cloud, a higher result validation degree can be selected.

Output Settings

Parameter Description

Maximum Number of Detected Poses in Each Point Cloud

Parameter description: This parameter sets the maximum number of output results in a single point cloud.
Default value: 1
Tuning instruction: If a single point cloud has multiple matching results, the results will be sorted in descending order according to the scores, and then the results with the highest scores will be output according to this parameter.

Advanced Parameter Tuning Level

Please refer to 3D Fine Matching.

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.