Page History

The pose The Pose detection is configured as follows:

1. Go to the Pose detection object settings panel, which is created on the basis of the Person location tracker object.
   

2. Configure the perspective of the video image:

   1. Click the Settings button (1). As a result, the Detection settings window will open.
      Image Added
      

   2. Click the Stop video button (1) to capture the video image.

   3. Specify at least three calibration segments in different parts of the frame (3). 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 the anchor points. The calibration segments should be located at different angles to each other depending on the scene and the distortion of the video image.
      Image Added
      

      Info
      title Note
      To delete the created segment, click theImage Addedbutton.

      
      

   4. Click the OK button (4).
3. Set the Trigger an alarm Generate alarm on camera check box checkbox (12) if it is also necessary to trigger an alarm on the camera by the specified pose detection.

4. In the Alarm border color field (3), specify the color of the alarm border using the color palette. The default color is red. Double click the color field to open the Color palette. After selecting the border color, click the OK button to save the settings.
   Image Added
   

5. In the Number of frames for decision making (1-20) field (4), enter the required amount of frames from 1 to 20 on which the human should be found in the specified pose to trigger the corresponding event. The default value is 2.

6. From the Position From the Type drop-down list (25), select the human type position which is necessary to detect:

   1. Sitting person detection

   — the

   1. —the detection triggers when a sitting human is found in the frame.

   2. Recumbent person detection

   — the

   1. —the detection triggers when a recumbent human is found in the frame.

   2. Hands up detection

   — the

   1. —the detection triggers when a human with

   one or two

   1. hands raised is found in the frame. The hand is considered

   to be

   1. being raised if the forearm is parallel to the backbone

   .

7. Active shooter detection — the detection triggers when a human reaching his/her hand forward parallel to the ground is found in the frame. 

1. and the wrists are above the shoulders. If this detection is selected, the following additional settings will become available:
   Image Added

   • Working mode—sets the hands position at which the alarm event will be generated.
2. Person detection—the detection triggers when a human in any pose
Person detection — the detection triggers when any pose of a human
1. is found in the frame.

8. In the Number of frames for making a decision (1-20) field (3), enter the required amount of frames from 1 to 20 on which the human must be found in the specified pose to trigger the corresponding event.

9. 1. Close-standing people detection—the detection triggers if the distance between two people is less than specified. If this detection is selected, the following additional settings will become available:
      Image Added
      
      • Calibration column length [0, 3]—sets the length of the calibration segments from 0 to 3 meters, which were set when adjusting the perspective of the video image. The default value is 1.7;
      • Distance sensitivity [0, 20]—sets the minimum distance between people from 0 to 20 meters. If the distance between people in the frame is equal to or less than the specified value, then the detection will be triggered. The default value is 2;
      • Number of people to alert [0, 20]—sets the number of people who should break the distance for the detection to be triggered. Possible values are from 2 to 20. The default value is 2

   Specify the perspective on the video image on which the human location will be detected:

   1. Click the Settings button (4). As a result, the Detection Settings window will open.
      Image Removed
      

   2. Click the Stop video button (1) to capture the video image.

   3. Specify the size of the same human at least in three different parts of the frame (2) with the calibration lengths. To create a calibration length, it is necessary to click and hold the left mouse button on the video image so that you can specify the necessary length size. Changing the size of the already created lengths is executed by using nodes.
      

      Info
      title Note
      To delete the created length, it is necessary to click theImage Removedbutton (3).

      Click the OK button (4)
      • .
10. Click the Apply button (56).

The pose The Pose detection is now configured.