.
To configure the Face Detection VL, do the following:
Go to the Detection Tools tab.
By default, the detection tool is enabled and set to detect faces.
If necessary, you can change the detection tool parameters. The list of parameters is given in the table:
| Parameter | Value | Description | |
|---|---|---|---|
| Object features | |||
| Check in lists | Yes | The Check in lists parameter is enabled by default. If you don’t want to use this detection tool for real-time face recognition (check in lists of faces), select the No value (see Configuring face recognition based on the created lists) | |
| No | |||
| Record objects tracking | Yes | The metadata of the video stream is recorded to the database by default. 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. For the correct operation of the Face Detection VL, we recommend using a high-quality video stream | |
| Second stream | |||
| Other | |||
| Enable | Yes | The detection tool is enabled by default. To disable the detection tool, select the No value | |
| No | |||
| Name | Face Detection VL | Enter the detection tool name or leave the default name | |
Decode key frames | Yes | The Decode key frames parameter is disabled by default. Using this option reduces the load on the Server, but at the same time the quality of detection is reduced. To decode only the key frames, select the Yes value. We recommend enabling this parameter for "blind" (without video image display) Servers on which you want to perform detection. For MJPEG codec decoding isn’t relevant, as each frame is considered a key frame | |
| No | |||
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 used for decoding | |
| CPU | |||
| GPU | |||
| HuaweiNPU | |||
| Frame size change | 640 | The analyzed frames are scaled down to a specified resolution (640 pixels on the longer side) by default. The value must be in the range [640, 10 000]. The following algorithm is used:
| |
| Type | Face Detection VL | Name of the detection tool type (non-editable field) | |
| Use camera transform | Yes | The Use camera transform parameter is disabled by default. If you use a XingYun bispherical lens (see Configuring fisheye cameras), by default the detection tool receives the image of two spheres of 180° each to analyze. In this case, the recognition quality can deteriorate. To send the dewarped image to the detection tool, select the Yes value. This parameter is also valid for other transformations | |
| No | |||
Advanced settings
| |||
| Analyze face rotation angle | Yes | The Analyze face rotation angle parameter is disabled by default. If you want to detect the face rotation angle, select the Yes value. This parameter allows you to filter out results that have a rotation and tilt angle greater than the specified values in a search for a specific face (see Search for similar face) | |
| No | |||
| Face recognition algorithm | Algorithm 1 | Select the face recognition algorithm:
| |
| Algorithm 2 | |||
| Algorithm 3 | |||
Face rotation pitch ( ° ) | 45 | Specify the allowable face pitch angle in degrees. The value must be in the range [0, 90] | |
| Face rotation roll ( ° ) | 45 | Specify the allowable face roll angle in degrees. The value must be in the range [0, 90] | |
Face rotation yaw from ( ° ) | -45 | Specify the minimum allowable angle of face rotation to the right or left. The value must be in the range [-90, 90] | |
Face rotation yaw to ( ° ) | 45 | Specify the maximum allowable angle of face rotation to the right or left. The value must be in the range [-90, 90] | |
Minimum image quality | 30 | Specify the minimum image quality for face detection. The value must be in the range [1, 100] | |
Minimum number of detections | 1 | Specify the minimum number of detections after which a track will be considered a detected face. The value must be in the range [1, 10 000] | |
Number of frames between detections | 3 | Specify the number of frames between detections. The lower the value, the higher the probability that TrackEngine will detect a new face as soon as it appears in the selected area. The value must be in the range [1, 10 000]
| |
Send face images | Yes | The Send face images parameter is disabled by default. If you want to send face images, select the Yes value
| |
| No | |||
Track timeout | 2 | Specify the maximum time period in seconds after which the event will be sent. The value must be in the range [1, 10 000] | |
| Basic settings | |||
| Biometric data | Yes | The Biometric data parameter is enabled by default. When searching for faces (see Search for all recognized faces), the search results will contain only found faces without an attached photo or a track. If you search for a similar face (see Search for similar face), there will be no results. To get results with an attached photo or a track when searching for faces (see Face search), select the No value | |
| No | |||
| Face attributes recognition | Yes | The Face attributes recognition parameter is disabled by default. If you want to save the gender and age information for each captured face to the database, select the Yes value
| |
| No | |||
| Medical mask detection | Yes | The Medical mask detection parameter is disabled by default. If you use mask detection, select the Yes value (see Configuring Masks Detection) | |
| No | |||
| Minimum face size | 10 | Specify the minimum size of the captured faces as a percentage of the frame size. The value must be in the range [1, 100] | |
| Minimum threshold of face authenticity | 60 | Specify the minimum level of face recognition accuracy for the creation of a track. You must select the relevant value empirically. We recommend specifying the value of not less than 90. The higher the value, the fewer faces are detected, while the recognition accuracy increases. The value must be in the range [1, 100] | |
| Mode | CPU | Select the processor for the detection tool operation—CPU or NVIDIA GPU (see General information on configuring detection)
| |
| Nvidia GPU 0 | |||
| Nvidia GPU 1 | |||
| Nvidia GPU 2 | |||
| Nvidia GPU 3 | |||
| Huawei NPU | |||
You can enable the advanced logging for SDK using the VL_SDK_VERBOSE_LOGGING=1 system variable (see Appendix 9. Creating system variable). |
If necessary, in the preview window, set the rectangular area of the frame, in which you want to detect faces. You can specify the area by moving the anchor points .
For convenience of configuration, you can "freeze" the frame. Click the The detection area is displayed by default. To hide it, click the |
To save the parameters of the detection tool, click the Apply 
button. To cancel the changes, click the Cancel 
button.
