-
Notifications
You must be signed in to change notification settings - Fork 1
DummyHumanPose
moscowsky edited this page Jun 5, 2024
·
1 revision
Hard-coded human poses based on keypoint detection.
Modes | Accuracy assessment | 3D-translation | 3D-rotation | Contour extraction | Additional info | Keypoints-labels |
---|---|---|---|---|---|---|
E | - | ❌ | ❌ | ❌ | <Attribute_name>:left_raised, <Attribute_name>:right_raised |
Now can detect left and right hands raised. Puts that info to the extracted_info
field.
Not implemented
Not implemented
Checks pose
- Name (string, must be set) attribute unique name
- Type (string, must be "DummyHumanPose") attribute type
- Weight (double, default: 1) attribute weight
- Probability (double, default: 0.75) acceptable detection accuracy, used in Detect mode.
- Contour (bool, default: true) Returns the contour of the attribute if true.
Not yet
<?xml version="1.0" ?>
- Home
- ROS-interface
- Interacting with a package through a configuration file
- Common structure of the configuration file
-
Simple objects
- Clusterization
- Filtering
- Tracking
- Attributes
- HSVcolor
- HistColor
- HaarCascade
- Size
- Hough
- Dimension
- BasicMotion
- Aruco
- Feature
- Pose
- DNN
- QR
- QR_Zbar
- LogicAnd
- LogicNot
- LogicOr
- Blob
- Depth
- RoughDist
- Dist
- FaceDlib
- ExractedInfoId
- ExractedInfoString
- UnitTranslation
- SquareObjectDistance
- TorchYOLOv7Attribute
- TorchYOLOv7KeypointAttribute
- ROSSubcriberOpenPoseRaw
- DummyHumanPose
- Complex objects
- Install Guides
- Usage Guides
- Troubleshooting