Versions Compared

Old Version 1

changes.mady.by.user Evgeniya Kononova

Saved on

compared with

New Version Current

changes.mady.by.user Alena Kniazeva

Saved on

Key

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

The When you export an archive, the AviExport utility allows for face masking in the exported video. This function is based on a neural network.

Info
titleNote.

Faces can also be masked on live video if the Face detection tool is in use – module is used—see Configuring Face detection tool.

Perform Configure the following settings to make the face masking function available:

  1. Install Detector Pack 2.6 or newer. The installation kit DetectorPack for the Remote Administrator’s workstation. The distribution package and documentation are available on the AxxonSoft web sitewebsite: https://www.axxonsoft.com/resourcessupport/downloads/intellect.phpaxxon-psim
  2. Enable the 64-bit modules – —see Configuring the use of using 64-bits bit modules.
  3. Select the export mode with data conversion and recompression in the AviExport utility – see Select export mode—see Selecting the format and recompression for the exported file.

As a result of the above steps, the Face disguise masking checkbox becomes available in the AviExport utility. If it the checkbox is set, then a mask appears over the faces in the exported file.

Image Removed

Example of face masking in the exported video:

Image RemovedImage Added

This function is configured using the SmallFacesDetector.config configuration file located in the Intellect software installation Axxon PSIM installation directory in the Modules64/caffewrapper folder.The following options can be configured You can configure the following parameters:

  • mode – mode—calculation mode: CPU or GPU.
  • deploy_file, model_file – file—neural network configuration file. At the time of this instruction publishingcreating the documentation, there are only those configuration files that are used by default, so it is not required to change these parameters.
  • count_classes – classes—number of classification classes (default 2). Do not change this setting.
  • trek_trsh – trsh—new face tracking threshold (default 0.2). After exceeding this threshold, face tracking is carried out taking into account the result_filter parameter.
  • result_filter – filter—confidence threshold (default 0). If the result of face recognition on the exported video is reliable with a probability above the specified threshold, then the face is considered detected. The higher the value, the less likely the false face recognition, but the greater the likelihood of skipping.

Configuration of face masking at export is complete.