HistColor - Extended-Object-Detection-ROS/wiki_english GitHub Wiki
An attribute that allows you to identify an object by color using histogram filtering. The theory of histogram filtering can be viewed here and here.
Modes | Accuracy assessment | 3D-translation | 3D-rotation | Contour extraction | Additional info |
---|---|---|---|---|---|
DC | C | ❌ | ❌ | ✔ | - |
Searches for connected regions of the specified color.
Checks if the specified percentage of object pixels meet the specified parameters.
Not implemented
- Name (string, must be set) attribute unique name
- Type (string, must be "HistColor") attribute type
- Weight (double, default: 1) attribute weight
- Probability (double, default: 0.75) acceptable detection accuracy, used in Check mode.
- Contour (bool, default: true) Returns the contour of the attribute if true.
- Histogram (must be provided) Path to .yaml file with histogram. If the path starts with '/', then it is considered global, if not, then local from the location of the object base.
<AttributeLib>
<Attribute Name="HistColorPink" Type="HistColor" Histogram="histograms/Pink.yaml"/>
</AttributeLib>
<SimpleObjectBase>
<SimpleObject Name="PinkSticker" ID="2">
<Attribute Type="Detect">HistColorPink</Attribute>
</SimpleObject>
</SimpleObjectBase>
As you can see, with color filtering, there may be small areas that match the color and the specified parameters. To filter them out, it is recommended to use size attribute on the image