DepthAttribute
A pseudo-attribute that determines the distance to the object from the map by its bordering rectangle and counts the translation into three-dimensional coordinates. If the object is outside the depth map, then the translation will not be added, and if there are no other attributes for extracting the distance, a standard unit transform will be added to the object.
| Modes | Accuracy assessment | 3D-translation | 3D-rotation | Contour extraction | Additional info |
|---|---|---|---|---|---|
| E | - | ✔ | ❌ | - | - |
Not implemented
Not implemented
Determines the distance to the object and calculates the translation vector in 3D space to the center of the object.
- Name (string, must be set) attribute unique name
- Type (string, must be "Depth") attribute type
- Weight (double, default: 1) attribute weight
- Probability (double, default: 0.75) not used in this attribute
- Contour (bool, default: true) not used in this attribute
- depthScale (double, default: 0.001) The relationship between the pixel value of the depth camera and the actual unit of measurement.
Important specify DEPTH in the Channel parameter in the object that uses this attribute.
<?xml version="1.0" ?>
<AttributeLib>
<Attribute Name="COCO_Dnn" Type="Dnn" framework="tensorflow" weights="ssd_mobilenet_v1_coco_2017_11_17/frozen_inference_graph.pb" config="ssd_mobilenet_v1_coco_2017_11_17/config.pbtxt" labels="ssd_mobilenet_v1_coco_2017_11_17/mscoco_label_map.pbtxt" inputWidth="300" inputHeight="300" Probability="0.75" obj_id="-1"/>
<Attribute Name="DepthKinect" Type="Depth" depthScale="0.001"/>
</AttributeLib>
<SimpleObjectBase>
<SimpleObject Name="COCO_dnn_object_depth" ID="64">
<Attribute Type="Detect">COCO_Dnn</Attribute>
<Attribute Type="Extract" Channel="DEPTH">DepthKinect</Attribute>
</SimpleObject>
</SimpleObjectBase>