To create the detection tool, do the following:

  1. Go to the Detection Tools tab.

  2. Below the required camera, click Create… → Category: Retail → Crowd Estimation VA.

By default, the detection tool is enabled and set to count crowds of people.

If necessary, you can change the settings of the detection tool parameters given in the table:

ParameterValueDescription
Object features
Record mask to archiveYesTo record the sensitivity scale of the detection tool to the archive (see Displaying information from a detection tool (mask)), select the Yes value
No
Video streamMain streamIf the camera supports multistreaming, select the stream for which detection is needed
Other
EnableYesBy default, the detection tool is enabled. To disable, select the No value
No
NameCrowd Estimation VAEnter the detection tool name or leave the default name
Decode key framesYes

By default, the Decode key frames parameter is enabled. In this case only key frames are decoded. To disable the parameter, select the No value in the corresponding field.

This parameter reduces the load on the Server, but at the same time the detection quality decreases. We recommend enabling this parameter for "blind" (without video image display) Servers on which you want to perform detection.

For the MJPEG codec decoding isn’t relevant, as each frame is considered as a key frame.

The Number of frames processed per second and Decode key frames parameters are interrelated.

If a local Client isn’t connected to the Server, the following rules work for remote Clients:

  • If the key frame rate is less than the value specified in the Number of frames processed per second field, the detection tool will work by key frames.
  • If the key frame rate is greater than the value specified in the Number of frames processed per second field, the detection will be performed according to the set period.

If a local Client is connected to the Server, the detection tool will always work according to the set period. After disconnecting the local Client, the above rules will be relevant again.


No
Decoder modeAuto

Select a processing resource for decoding video. 

When you select a GPU, a stand-alone graphics card takes priority (when decoding with NVIDIA NVDEC chips). If there is no appropriate GPU, the decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources will be used for decoding

CPU
GPU
HuaweiNPU
ModeCPU

Select the processor for the operation—CPU or NVIDIA GPU (see General information on configuring detection).

  • If you specify other processing resource than the CPU, this device will carry the most of computing load. However, the CPU will also be used to run the Crowd Estimation VA .
  • Starting with Detector Pack 3.11, Intel HDDL and Intel NCS aren’t supported.


Nvidia GPU 0
Number of alarm objects1

Specify the number of objects that will trigger the detection. The value must be in the range [0; 10000]

Number of frames processed per second0.25

Specify the number of frames for the detection tool to process per second. The value must be in the range [0.016; 100]

Trigger upon count

Greater than or equal to threshold value

Select when you want to generate a trigger.

The Crowd Estimation VA will generate a trigger from the threshold value set in the Number of alarm objects field

Less than or equal to threshold value
TypeCrowd Estimation VAName of the detection tool type (non-editable field)

If necessary, in the preview window, set detection areas with the help of anchor points (the same as with the excluded areas of the Scene analytics detection tools, see Setting General Zones for Scene analytics detection tools). By default, the whole frame is a detection area.

To save the parameters of the detection tool, click the Apply  button.

To cancel the changes, click the Cancel button.

It is possible to display the sensor and the number of objects in the monitored area in the Surveillance window on the layout (see Displaying the number of detected objects).