Versions Compared

Old Version 11

changes.mady.by.user Alina Luchkina

Saved on

compared with

New Version 12

changes.mady.by.user Bahdan Tsiulkou

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Tip

Video stream and scene requirements for the Person-based privacy masking

Hardware requirements for neural analytics operation

To configure the Person-based privacy masking detector, do the following:

  1. Go to the
    2.  Detection Tools
  2. Detectors tab.
  3. Below the required camera, click Create… → Category: Poses → Person-based privacy masking.

By default, the detection tool detector is enabled and set to mask a person's head.

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

neural network mode (see  other will carry the  However will be detection tool with  3
ParameterValueDescription
Object features
Record mask to archiveYesBy default, the recording of the mask to the archive is disabledenabled. To record mask to the archive (see Displaying information from a detector (mask)), select the Yes valuedisable, select the No value
No
Video streamMain streamIf the camera supports multistreaming, select the stream for which detection is needed. Selecting a low-quality video stream allows reducing the load on the Serverserver
Second stream
Other 
EnableYesThe detection tool detector is enabled by default. To disable the detection tool, select the No value value
No
NamePerson-based privacy maskingEnter the detection tool detector name or leave the default name
Decoder modeAutoSelect 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 second1Specify the number of frames that the detection tool detector will process per second. The value must be in the range range [0.016; 100]
TypePerson-based privacy maskingName of the detection tool detector type (non-editable field)
Advanced settings
Number of measurements in a row to trigger detection3Specify the minimum number of frames on which the detection tool detector must detect objects to generate an event. The value must be in the range [1, 20]
Segmenting network file

Select Specify a neural network file.

The standard neural networks for different processor types are located in the C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK directory. You don't need to select the standard neural networks in this field, the system will automatically select the required one. If you use a custom neural network, specify the path to the file.

Infonote
titleNoteAttention!
  • 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
To ensure the correct operation of the neural network
  • on Linux OS, place the corresponding file
must be located
  • locally in the /opt/AxxonSoft/DetectorPack/NeuroSDK directory
. 
Note
titleAttention!
  • or in the network folder with the corresponding access rights.
  • If you use a standard neural network (training wasn't performed in operating conditions), we guarantee the overall accuracy of 80-95% and the percentage of false positives of 5-20% (see Data collection requirements for neural network training).
Basic settings
Detection modeCPU

Select the

detector operation mode (see Hardware requirements for neural analytics operation, Selecting Nvidia GPU when configuring detectors).

Note
titleAttention!
  • another processing resource than the CPU, this device
  • carries most of the computing load.
  •  However, the CPU
  • is also
  • used to run the
  • detector.
  • 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 GPU
Intel HDDL NCS (not supported)
Intel Multi-GPU
Intel GPU 0
Intel GPU 1
Intel GPU 2
Intel GPU 3
Intel HDDL NCS (not supported)
Mask
BodyYesBy default, the detection tool detector masks only a person's head. To mask other parts of the body, select the Yes value for the corresponding parameters 
No
FeetYes
No
ForearmsYes
No
HandsYes
No
HeadYes
No
HipsYes
No
ShinsYes
No
ShouldersYes
No

By default, the entire frame is a detection area. 

To save the parameters of the detection tooldetector, click the the Apply Image Modified button. To cancel the changes, click the Cancel Image Modified button.

Configuring the Person-based privacy masking is complete. 

Selected body parts of all persons will be are hidden in the frame. For a user group with limited permissions to view masked video (see Roles), the mask is displayed on the video image of the selected camera in the Detection Tools and Detectors and Hardware sections, on the layouts, in the archive, and when exporting. For the admin user group, the mask is displayed only on the video image of the selected camera in the Detection Tools Detectors and Hardware sections, and when exporting, if the View masked video checkbox is clear (see Standard video recordings export).
Image Modified