Documentation for Axxon One 1.0.

Previous page Optimization of Face detection on GPU  Fine-tuning the face detection (VL) Next page

To configure the Face detection (VL), do the following:

  1. Select the Face detection (VL) object. 
  2. If you need to use this detection tool for real-time face recognition, set the corresponding parameter to Yes (1, see Configuring real-time face recognition).
  3. If you need to record metadata, select Yes from the Record objects tracking list (2).
  4. If the camera supports multistreaming, select the stream for which detection is needed (3). For the correct operation of the Face detection (VL), it is recommended to use a High-quality video stream.
  5. Select a processing resource for decoding video streams (4). 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.
  6. In the Face attributes recognition field (5), select Yes if it is necessary to recognize gender and age.
  7. Set the maximum size of the captured faces as a percentage of the frame size (6).
  8. If necessary, set Yes for the Medical mask detection parameter (7, see Configuring masks detection).
  9. Set the minimum size of the captured faces as a percentage of the frame size (8).
  10. Set the Minimum image quality of a person's face for face detection (9). A required value should be selected empirically, at least 50 is recommended.
  11. In the Minimum threshold of face authenticity field (10), set the minimum level of face recognition accuracy for the creation of a track. A required value should be selected empirically, at least 90 is recommended. The higher the value, the higher the recognition quality will be.

  12. Select the processor for the face detection − CPU or NVIDIA GPU (11, see General Information on Configuring Detection).

    Attention!

    It may take several minutes to launch the algorithm on an NVIDIA GPU after you apply the settings.

  13. If FaceCube integration is used (see Configuring FaceCube integration), enable the Send face images parameter (12).
  14. If necessary, fine-tune the detection tool (see Fine-tuning the face detection (VL)).
  15. In the preview window, set the rectangular area of the frame where faces should be detected. To select the area, move the anchor points .
  16. Click the Apply button.

The Face detection (VL) is now configured.

  • No labels

Fine-tuning the face detection (VL)

License activation for Face detection (VL)