2D Alignment
Description
This Step aligns the input image with the template via translation and rotation, ensuring the consistency between the two.
Input and Output
Input
| Input port | Data type | Description |
|---|---|---|
Image |
Image |
Image used for template matching. |
Alignment Parameter Group |
Pose2D |
Used to adjust the target region’s pose in sync with the target object’s pose changes. |
Output
| Output port | Data type | Description |
|---|---|---|
Aligned Image |
Image |
The image after alignment. |
Matching Score |
Number |
Used to evaluate the match quality. |
Alignment Parameter Group |
Pose2D |
The translation and rotation parameters required to align matched objects with the template. |
Object Pose |
Pose2D |
The position and orientation of the matched objects in the image. |
Min bounding box |
Shape2D/Rectangle |
The minimum bounding box of the matched object. |
Parameter Description
| Parameter | Description |
|---|---|
ROI settings |
The ROI is used to define the image area to be processed by the algorithm. Once this parameter is selected, the Step will only use the data in the ROI to match the template. |
Mask settings |
For template matching, the system ignores the image regions covered by the masks. For the mask settings and adjustment methods, refer to ROI Settings. |
Template Settings
| Parameter | Description |
|---|---|
Select Template |
This parameter is used to specify the matching template. Click Open the editor to open 2D Template Editor, where you can edit the template for alignment. After specifying and saving the template, click ▼ and select the template in the drop-down menu. For instructions on how to use the editor, see 2D Template Editor. |
Matching Settings
Frequently Used Parameters
| Parameter | Description |
|---|---|
Edge Polarity Sensitive |
This parameter controls whether edge polarity must match the template. The polarity indicates the direction of intensity changes along the edges, e.g., light-to-dark or dark-to-light. If there is not a large disparity in the data acquisition scenarios, enable this option to ensure matching accuracy. If there is a large disparity, disable this option to enhance the matching generalization ability. Enabled by default. |
Min Matching Score |
This parameter is used to determine whether a matching result is valid. Any result whose score is below this value will be discarded. Default setting: 50.0 |
Advanced Parameters
| Parameter | Description | ||
|---|---|---|---|
Valid Matching Threshold |
In the target image, points with gradient magnitudes greater than or equal to this threshold are considered valid edge points and participate in matching score calculation. Default value: 10 |
||
Min Valid Match Ratio |
The minimum ratio of valid matched edge points to the total number of edge points in the template. Default value: 50% |
||
Search Radius |
The radius of the circular search area for finding corresponding matching points of each template feature point in the target image during pose refinement. Default value: 8
|
||
Max Overlap Ratio |
Used to filter out duplicate matching results. If there is an overlap between two matching results and the overlap ratio exceeds this value, only the result with the higher matching score will be retained. Default value: 50% |
||
Padding Ratio |
Specifies the ratio of allowed padded size to template size when the target object may be partially outside the image. Padding can recover edge matches that would otherwise fail, but generally increases computation.
|