Go to documentation repository
Previous page Next page
The pose detection is configured as follows:
Specify the perspective on the video image on which the human location will be detected:
Click the Settings button (1). As a result, the Detection settings window will open.
Click the Stop video button (1) to capture the video image.
Specify the size of the same human at least in three different parts of the frame (2) with the calibration segments. To create a calibration segment, click and hold the left mouse button on the video image so that you can specify the necessary length size. You can change the size of the already created segments using nodes. The calibration segments should be located at different angles to each other depending on the scene and the distortion of the video image.
Note
From the Type drop-down list (4), select the human type which is necessary to detect:
Sitting person detection — the detection triggers when a sitting human is found in the frame.
Recumbent person detection — the detection triggers when a recumbent human is found in the frame.
Hands up detection — the detection triggers when a human with hands raised is found in the frame. The hand is considered to be raised if the forearm is parallel to the backbone. If this type is selected, the following additional settings will become available:
Active shooter detection — the detection triggers when a human reaching his/her hand forward parallel to the ground is found in the frame.
Person detection — the detection triggers when any pose of a human is found in the frame.
The pose detection is now configured.