Previous page Types of retail analytics detection tools  Configuring the visitors counter Next page

To configure the queue detection tool, do the following:

  1. By default, the frame is compressed to 1920 pixels on the longer side. To avoid detection errors on streams with a higher resolution, it is recommended that compression be reduced (1).
  2. In the Interval between processed frames (3) field, specify the time period in milliseconds between frames analyzed by the people counter within the area. The value should be within the range of 500 – 3000. The smaller the value of this parameter, the greater the CPU load.
  3. Specify the number of people to trigger the alarm when exceeded (3). The value should be within the range of 2 – 20. 
  4. Specify the detection tool sensitivity in standard units from 0 to 1 (4). The higher the sensitivity, the smaller the disturbances analyzed by the queue detection algorithm. Alternatively, the lower the sensitivity, the greater changes in scene are processed by the queue detection tool.
    You should set the sensitivity value empirically based on the Motion Mask data displayed in the Preview window.
  5. In the Preview window, you can set the detection zones with the help of anchor points much like privacy masks in Scene Analytics.
  6. Click  and set the approximate size of a human. You can do so by dragging the corners of the rectangular area.
  7. Click Apply.

The queue detection tool is now configured. When the detection tool is triggered, the following events are generated:

Camera "6. Camera". Detection "Queue detection" triggered, quaue (min.: 6, max.: 6)

where min. and max. is estimated queue length. 

  • No labels