To configure the Privacy Maskingmasking detector, do the following:
- Go to the
...
- Detectors tab.
Below the required camera, click Create… → Category: Trackers → Privacy
...
masking.
By default, the detection tool detector is enabled and set to hide stationary objects.
| Note |
|---|
|
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:
| 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 |
|---|
| 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 |
Masking 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 | |
detection tools other - another processing resource than the CPU, this device
|
|
will carry the - carries most of the computing load. However, the CPU
|
|
will be detection tool |
| 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. |
is not specified 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 - If you use a standard neural network (training wasn't performed in operating conditions), we guarantee an overall accuracy of 80-95% and 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:
| Info |
|---|
|
- 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 the
 Image Modified button. To cancel the action, click this button again.
|
To save the parameters of the detection tooldetector, click the Apply 
Image Modified button. To cancel the changes, click the Cancel 
Image Modified button.
Configuration of the Privacy Masking Configuring the privacy masking is complete.
Image Modified
...
...
