To configure the PPE detection tool (VL), do the following:

  1. To record the tracks of captured faces to the database, select Yes in the Record objects tracking parameter (1).
  2. If the camera supports multistreaming, in the Video stream from camera field select the stream for which detection is needed (2). 
  3. In the Decoder mode field, select a processor for video decoding (3). 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 (see General Information on Configuring Detection).

  4. Set the frame rate value for the detection tool to process per second (4). This value should be in the range [0,016; 100]. 

  5. In the Minimum threshold of face authenticity field, set the minimum level of face recognition accuracy for creating a track (5). The value should be in the range [1; 100].

    An appropriate value should be selected empirically; at least 90 is recommended. The higher the value, the higher the recognition quality will be.


  6. In the Mode field, select a processor for the neural network operation: CPU, one of GPUs, or one of Intel processors (6, see Hardware requirements for neural analytics operation, General Information on Configuring Detection).

    It may take several minutes to launch the algorithm on NVIDIA GPU after you apply the settings. You can use caching to speed up future launches (see Configuring the acceleration of GPU-based neuroanalytics).


    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 detection tool.


  7. In the Number of measurements in a row to trigger detection field, set the minimum number of frames on which the detection tool should detect a violation in order to generate a trigger (7). The value should be in the range [1; 20].
  8. By default, a detection tool trigger for each item of equipment will be generated once within the existence of a person's track. If it is necessary to generate a trigger for each equipment violation, then select No in the One detection per track parameter (8).

The PPE detection tool (VL) is configured.