Separator and Slip Sheet Detection Guide
The Separator and Slip Sheet Detection function is mainly used in ordered scenarios where each layer of workpieces has a separator underneath, and the separator and slip sheet still need to be picked after the workpieces have been picked. This article mainly introduces how to set up and use this function after enabling Separator and Slip Sheet Detection.
1. Operation Guide
When each layer of workpieces in the actual scene has a separator underneath, enable the Separator and Slip Sheet Detection function when creating a new project or a new task; if it was not enabled when creating the new project or task, go to the task Information page, click Edit in the lower right corner, and then enable Separator and Slip Sheet Detection
After adding the plugin, add a new workpiece on the workpiece page. Click the Enter Type button under Workpiece Information - Vision Classification to enter types for the workpiece, separator, and slip sheet respectively.
Type Entry
For details, refer to: Vision Classification Guide
Click + to add a type
Fill in the type id
Take a photo or import an image
Select the corresponding image area in the image. The selected area must be consistent with the roi2d area. Enter at least 10 samples for each type
Adjust parameters
| Parameter | Description | Default Value | Value Range | Tuning Suggestion |
|---|---|---|---|---|
| Scale Ratio | Scale the images in the entered type database to extract image features. The smaller the scale ratio, the faster the category information is calculated. | 1.0 | 0.1 - 2.0 | 1.0 |
| Augment Data by Rotation | Rotate the entered type images to augment the number of images in the type database | Checked | / | / |
| Image Rotation Count | After checking Augment Data by Rotation, the number of images in the database is augmented according to the Image Rotation Count. For example, if the image rotation count is 4, the image rotates counterclockwise by 90° (360°/4) each time, for a total of 4 rotations; if the image rotation count is 3, the image rotates counterclockwise by 120° (360°/3) each time, for a total of 3 rotations | 2 | [1,360] | The larger the value, the more image angles are augmented |
After testing the entered types, open Robot Configuration and add the workpiece type command token ‘{cid}’ to the vision detection send command
2. Tuning Guide
By adjusting visual parameters, the vision system can better distinguish and recognize separators and slip sheets based on the entered classification data.
Separator and Slip Sheet Detection uses the Top-layer Texture Extraction function by default, so most parameters are the same as those for Extract Top-layer Texture.
| Parameter | Description | Default Value | Value Range | Tuning Suggestion |
|---|---|---|---|---|
| Distance Threshold (m) | The upper distance threshold for top-layer plane extraction. Points whose distance from the plane is lower than this value are considered to be points on the plane; otherwise, they are considered to be outside the plane. Unit: m | 0.05 | 0.0001-1 | Adjust the distance threshold according to the workpiece height, usually 1/2 of the height |
| Clustering Point Cloud Count | Expected number of points participating in clustering | 10000 | 1-10000000 | The more clustering Point Cloud points there are, the slower the model Inference speed and the higher the accuracy; the fewer there are, the faster the model Inference speed and the lower the accuracy |
| Minimum Number of Category Points | Minimum number of points used to filter categories | 1000 | 1-10000000 | / |
| Automatically Calculate Contrasting Background | After checking, black or white with a large contrast difference is automatically calculated according to the hue of the current instance | Checked | / | / |
| Background Color Threshold | When 'Automatically Calculate Contrasting Background' is checked, if the instance color value is greater than 'Background Color Threshold', the Background is set to black; otherwise, it is set to white. When 'Automatically Calculate Contrasting Background' is not checked, this parameter value is the Background color itself. Note that 0 is black and 255 is white | 128 | 0-255 | / |
| Save Image Classifier Data | Save image classifier data when checked | Unchecked | / | When checked, data will be saved, increasing time consumption; it is recommended to enable this in the early stage when classification data needs to be supplemented |
| Inference Scale Ratio | Scale ratio used during Image Classification Inference | 1.0 | 0.01-1.0 | Keep it consistent with the Scale Ratio in type entry |