Page History

The Person location tracker software module is configured on the Person location tracker object settings panel. This object is created under the Camera object on the Hardware tab of the System settings window.

Image Modified

The Person location tracker software module is configured as follows:

1. Go to the Person location tracker object settings panel.
   
2. Set the Show objects on image checkbox (1) if it is necessary to highlight the detected object with a frame when viewing live video.

3. From the Device drop-down list (2) select the device where the neural network will operate.

4. Select the required neural network file with the tracking model (3).

5. In the Frames processed per second [0,016, 100] field (4), set the number of frames per second that will be processed by the detection tool.

   Note
   title Attention!
   For scene with static people, the fps value should be at least 2. For scene with moving people — at least 4. The larger this value, the higher the accuracy of pose detection, but the greater the CPU load. With fps=1, the accuracy will be no less than 70%. This parameter varies depending on the object speed of movement. To solve typical tasks, fps value from 3 to 20 is sufficient. Examples: pose detection for moderately moving objects (without sudden movements) — fps=3; pose detection for moving objects — fps=12.

   
   

6. In the Object life span (ms) field (5), enter the time in milliseconds in which the found object will be considered as disappeared from the frame.

7. Click the Settings button (6). As a result, the Detection settings window will open.
   

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

   2. Click the Area of interest button (2) and specify the area in which the Person location tracker will operate (3).
      Image Added

      Info
      title Note
      To delete the selected area, click the Image Removed Image Added button.

      
      

   3. Click OK button (4).

8. Click the Apply button (7).

9. Perform pose detection configuration (see Configuring the Pose detection).