Pose Estimation
Description
Pose estimation is a tool that allows the user to detect human key points in images using a pre-trained model.
Settings
Pose Estimation model
Pre-trained models for pose estimation, here are the supported models:
- MoveNet Lightning Single Pose
- Fastest interference speed, moderate accuracy and single pose only.
- MoveNet Lightning Multi Pose
- Fast interference speed, moderate accuracy and multi pose.
- MoveNet Thunder Single Pose
- Moderate interference speed, higher accuracy and single pose only.
- CenterNet
- Slow interference speed, highest accuracy and multi pose.
Bounding boxes Confidence Threshold
The bounding boxes confidence threshold is the minimum confidence score a bounding box should have to be considered valid. Bounding boxes with confidence scores below this threshold will be discarded. A higher confidence threshold will result in fewer bounding boxes, but with higher accuracy, whereas a lower threshold will result in more bounding boxes, but with potentially lower accuracy.
Key points Confidence Threshold
The key points confidence threshold is the minimum confidence score a key point should have to be considered valid. Key points with confidence scores below this threshold will be discarded. A higher confidence threshold will result in fewer key points, but with higher accuracy, whereas a lower threshold will result in more key points, but with potentially lower accuracy.
Detect lying down
Whether to enabled detecting for someone lying down (fell down).
The detector may produce false positives or false negatives. In certain image angles, the detector may not be able to detect whether the person is lying down.
Please use this detector with caution.
Head and shoulder angle threshold
The threshold angle (degrees) from upright from the hips to the shoulders where the detector detects whether the person is lying down.
Knee and hip angle threshold
The threshold angle (degrees) from upright from the hips to the knees where the detector detects whether the person is lying down.
Lying buffer time (seconds)
The buffer time (seconds) for the detector to detect whether the person is lying down. This is to reduce false positives, the default value is 1 second but can be set to 0 to disable the buffer time.
If the buffer time is set to 0, the detector will be more sensitive to false positives. Please use this setting with caution.
Display Results
Overlay Results
Whether to draw the results on top of the image frame.
Draw Labels
Whether to draw the results on top of the image frame.