Page History

Tip

To configure the Privacy Maskingmasking detector, do the following:

Go to the Detection ToolsDetectors tab.
Below the required camera, click Create… → Category: Trackers → Privacy Maskingmasking.

By default, the detection tool detector is enabled and set to hide stationary objects.

Note

title	Attention!

We don't guarantee the correctness of detector operation earlier than 10 minutes from the moment of detector creation or making any changes in the detector settings.

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

detection tools other will carry the will be detection tool

Parameter

Value

Description

Object features

Record mask to archive

Yes

By default, mask is the mask is recorded to the archive. To disable the parameter, select the No value

No

Video stream

Main stream

If the camera supports multistreaming, select the stream for which detection is needed. Selecting a low-quality video stream reduces the load on the Serverserver.

Note

title	Attention!

To ensure the correct display of streams on a multi-stream camera, all video streams must have the same frame aspect ratio.

Other

Enable

Yes

By default, the detection tool detector is enabled. To disable, select the No value

No

Name

Privacy Maskingmasking

Enter the detection tool detector name or leave the default name

Decoder mode

Auto

Select a processing resource for decoding video streams. 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 are used for decoding

CPU

GPU

HuaweiNPU

Number of frames processed per second

25

Specify the number of frames for the detector to process per second. For sub-detectors to work correctly, the Privacy masking detector must analyze frames at least every 0.5 seconds. The value must be in the range [0.016, 100]

Type

Privacy Masking

Name of the detection tool type detector type (non-editable field)

Basic settings

Detection threshold

15

Specify the Detection threshold for objects in percent. If the recognition probability falls below the specified value, the data will be is ignored. The higher the value, the higher the sensitivity to recognizing and masking objects. The value must be in the range [5, 100]

Neural network mode

CPU

Select a processing resource for neural network operation (see Hardware requirements for neural analytics operation, Selecting Nvidia GPU when configuring

detectors).

Note

title	Attention!

If you specify

another processing resource than the CPU, this device

carries most of the computing load. However, the CPU

is also

used to run the

detector.
It may take several minutes to launch the algorithm on the Nvidia GPU after you apply the settings. You can use caching to speed up future launches (see Optimizing the operation of neural analytics on GPU in Windows OS, Optimizing the operation of neural analytics on GPU in Linux OS).
Starting with Detector Pack 3.11, Intel HDDL and Intel NCS aren’t supported.
Starting with Detector Pack 3.14, Intel Multi-GPU and Intel GPU 0-3 are supported.

Nvidia GPU 0

Nvidia GPU 1

Nvidia GPU 2

Nvidia GPU 3

Intel NCS NCS (not supported)

Intel HDDL (not supported)

Intel GPU

Intel Multi-GPU

Intel GPU 0

Intel GPU 1

Intel GPU 2

Intel GPU 3

Huawei NPU

Neural network filter

Neural network

Yes

By default, the parameter is disabled. The detection tool detector works on the basis of an algorithm without a neural network, ignoring the value specified in the Neural network file parameter. If the detection tool detector cannot correctly detect an object in the frame, select the Yes value. In the Neural network file parameter, select a custom neural network that is a privacy mask neural network. A detection tool detector with a neural network algorithm based on this neural network will be is created

No

Neural network file

If you use a custom neural network, select the corresponding file.

Note

title	Attention!

To train your neural network, contact AxxonSoft (see Data collection requirements for neural network training).
If you don't specify the neural network file is not specified, the default file will be is used that is selected automatically depending on the selected processor for the neural network operation (Decoder mode). If you use a custom neural network, enter a path to the file.
To ensure the correct operation of the neural network in Linux OS, the corresponding file must be located in the /opt/AxxonSoft/DetectorPack/NeuroSDK directory.
If you use a standard neural network (training wasn't performed in operating conditions), we guarantee

the

an overall accuracy of 80-95% and

the

a percentage of false positives of 5-20%. The standard neural networks are located in the C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK directory.
You cannot specify the network file in Windows OS. You must place the neural network file locally, that is, on the same server where you install Axxon One.
For correct neural network operation on Linux OS, place the corresponding file locally in the /opt/AxxonSoft/DetectorPack/NeuroSDK directory or in the network folder with the corresponding access rights.

Neural network recognition threshold
(starting with Detector Pack 3.15)

0

Specify the neural network recognition threshold in percentage. If the probability of neural network recognition is lower than the specified one, this data is ignored. The higher the value, the higher the sensitivity to the recognition. The value must be in the range [0, 100]

Selected object classes
(starting with Detector Pack 3.15)

If necessary, specify the object class of the detection neural network (the Neural network file parameter)

By default, the entire frame is a detection area. If you want to exclude from analysis difficult areas in the camera FOV (foliage, water, and so on), specify one or more skip areas (see Configuring a skip area), within which detection won't be performedIf necessary, in the preview window, set one or more:

detection areas (see Configuring a detection area),
ignore areas (see Configuring the ignore area).

Info

title	Note

For convenience of configuration, you can "freeze" the frame. Click the Image Modified button. To cancel the action, click this button again.
The detection area is displayed by default. To hide it, click theImage Modified button. To cancel the action, click this button again.