Video detection based on the Pose-Detection model of the tensor-flow library.

Returns array's of keypoints coordinates, see the diagram below for what those keypoints are and their index in the array.

0: nose
1: left_eye
2: right_eye
3: left_ear
4: right_ear
5: left_shoulder
6: right_shoulder
7: left_elbow
8: right_elbow
9: left_wrist
10: right_wrist
11: left_hip
12: right_hip
13: left_knee
14: right_knee
15: left_ankle
16: right_ankle
Bypasses the module processing when activated (ON).
Video input flow(s).
Video output flow(s).
Total time used for the calculation of the module.
X coordinates of the keypoints.
Y coordinates of the keypoints.
Confidence of the keypoints as float a value from 0 (bad detection) to 1 (good detection).
Opens the web browser to display information or help about the selected object, if it exists.
For more details about information/help creation, see create-help-file.
Description of the module for internal help purposes only. The description is not displayed in the interface.
visible only in god mode, see setup-panel-tab-expert.
Current private ID for this control used to identify the object.
Current private preset ID for this control used for presets.
If you experience difficulties in Polyphonic mode, try to recreate new id(s) with this button.
Each Patch shared on the local network uses its own ID (identification number). If you experience issues of Patches that don't send information to the good target, this button will rebuild all these id's.
Absolute remote address. see objects-address.
Local to the current patch remote address. see objects-address.
User defined remote address. see objects-address.
version 7.0.250121
Edit All Pages