Versions Compared

Old Version 3

changes.mady.by.user Darya Andryieuskaya

Saved on

compared with

New Version Current

changes.mady.by.user Bahdan Tsiulkou

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Section
Column
width50%
Panel
borderColor#CCCCCC
bgColor#FFFFFF
titleBGColor#F0F0F0
borderStylesolid
titleOn the page:

Table of Contents


Column


Configuring the parameters

To create the Sitting person detector, do the following:

  1. Create the Human pose detector (see Configuring the Human pose detector).
  2. Below the Human pose detector, click Create… → Sitting person detector.

By default, the Sitting person detector generates an event if a sitting person is detected in the specified area.

If necessary, you can change the detector parameters. The list of parameters is given in the table:

ParameterValueDescription
Other
EnableYesThe detector is enabled by default. To disable the detector, select the No value
No
Name Sitting person detectorEnter the detector name or leave the default name
TypeSitting person detectorName of the detector type (non-editable field)
Basic settings
Number of measurements in a row to trigger detection2

Specify the minimum number of frames with the corresponding pose or behavior for the detector to generate an event. The value must be in the range [1, 20].
The recommended (default) value is 2.
Increasing the value can help eliminate false events, but increases the risk of skips. 
Decreasing the value can help reduce skips, but increases the probability of false events

To save the parameters of the detector, click the Apply Image Added button. To cancel the changes, click the Cancel Image Added button.

Configuring the detection area

To configure the detection area, do the following:

  1. In the preview window, click the Image Added button.
  2. Click in the preview window.
  3. Select Detection area.
    Image Added

  4. Using the anchor points Image Added, set the detection area in which a sitting person must be detected.
    Info
    titleNote
    • For convenience of configuration, you can "freeze" the frame. Click the Image Added button. To cancel the action, click this button again.
    • To hide the detection area, click the Image Added button. To cancel the action, click this button again.
    • To delete the detection area, click the Image Added button.

  5. Click the Apply Image Added button.

Configuration of the detection area is complete.

Configuring the frame perspective 

If a camera angle doesn't meet the requirements (see Video stream and scene requirements for the Human pose detector and its sub-detectors), this can result in false events. In this case, we recommend configuring the frame perspective using the leveling rods. 

For

Tip

Setting up common parameters for Pose detection tools

To detect a sitting pose, you should configure frame perspective first.

To do this, do the following:

  1. In the preview window, click the Image Added button.
  2. Click
    3. Select a detection tool, and click the Image Removed button
  3. in the preview window.
    4. Set
  5. Select Leveling rod.
    Image Added
  6. Specify the size of the same person in different
    7. areas
  7. parts of the
    8. FOV.
  8. frame by eye: 
    • To create a leveling rod, left-click
    9. on
    • the video image to add two anchor points.
    10. You should set

    • Set at least three

    11. leveling rods. 

    • calibration rods. The lower anchor points of any three rods must not be located on the same line (horizontal, vertical, slanting, and so on).

    • The size of the leveling rod
    12. should
    • must be about the average height of a person at this
    13. point in
    • part of the frame.
    • You can resize the rod by stretching its anchor points
    14.  Image Removed
    15. Image Removed
    • Image Added

      Note
      titleAttention!

      When

    16. setting

    • you set up

    17. the

    • leveling rods, the following conditions

    18. should

    • must be met:

    19. The
      1. the rods that are located at the same distance from the
    20. video
      1. camera lens
    21. , should
      1. must be of the same size
    22. .
      1. ;
    23. The
      1. the feet of the rods
    24. should
      1. must be located on the same surface (
    25. e.g.
      1. for example, floor)
    26. .
      1. ;
    27. In

      1. in complex scenes,

    28. it is recommended to add

      1. we recommend adding more than three rods to increase the accuracy of the detection

    29. .

      1. ;

    30. In

      1. in the parts of the frame where the lens vertical distortion is observed, the rods

    31. should

      1. must be parallel to the nearest vertical objects (

    32. e.g.

      1. for example, door, wardrobe)

    33. .

      1. ;

    34. For
      1. for portrait-oriented scenes (such as corridor, shopping aisle, warehouse aisle,
    35. etc.
      1. and so on), the arrangement of the rods
    36. should
      1. must form triangles.

      Info
      titleNote
      • For
    37. your
      • convenience of configuration, you can "freeze" the frame. Click the Image Added button. To cancel the action, click
    38. the Image Removed
      • this button again.
      • The area for detection is displayed by default. To hide it, click the Image Added button. To cancel the action
    39. button and configure the mask on a still frame. To undo
      • , click this button again.
    40. info
    41. titleNote
      • To delete
    42. the
      • a rod, click the
    43. Image Removed button
      • Image Added button.
  44. Click the Apply Image Added button.

Configuring Configuration of the Sitting person detection tool detector is complete.